Join Cartesia as an Inference EngineerAt Cartesia, our vision is to create the next evolution of AI: an interactive, omnipresent intelligence that operates seamlessly across all environments. Currently, even the most advanced models struggle to continuously analyze a year's worth of audio, video, and text data—comprising 1 billion text tokens, 10 billion audio tokens, and 1 trillion video tokens—much less perform these tasks on-device.We are at the forefront of developing the model architectures that will make this a reality. Our founding team, who met as PhD candidates at the Stanford AI Lab, pioneered State Space Models (SSMs), a groundbreaking framework for training efficient, large-scale foundation models. Our talented team merges deep expertise in model innovation and systems engineering with a design-focused product engineering approach, enabling us to build and launch state-of-the-art models and user experiences.Supported by leading investors such as Index Ventures and Lightspeed Venture Partners, along with contributions from Factory, Conviction, A Star, General Catalyst, SV Angel, Databricks, and others, we are fortunate to be guided by numerous exceptional advisors and over 90 angel investors from diverse industries, including some of the world’s foremost experts in AI.About the RoleWe are actively seeking an Inference Engineer to propel our mission of creating real-time multimodal intelligence.Your ImpactDevelop and implement a low-latency, scalable, and dependable model inference and serving stack for our innovative foundation models utilizing Transformers, SSMs, and hybrid models.Collaborate closely with our research team and product engineers to efficiently deliver our product suite in a fast, cost-effective, and reliable manner.Construct robust inference infrastructure and monitoring systems for our product offerings.Enjoy substantial autonomy in shaping our products and directly influencing how cutting-edge AI is integrated across diverse devices and applications.What You BringAt Cartesia, we prioritize strong engineering skills due to the complexity and scale of the challenges we tackle.Proficient engineering skills with a comfort level in navigating intricate codebases, and a commitment to producing clean, maintainable code.Experience in developing large-scale distributed systems with strict performance, reliability, and observability requirements.Proven technical leadership, capable of executing and delivering results from zero to one amidst uncertainty.A background in or experience with inference pipelines, machine learning, and generative models.

About CartesiaAt Cartesia, we are on a mission to revolutionize AI by creating interactive intelligence that is seamlessly integrated into your daily life. Currently, existing models struggle to continuously analyze vast streams of audio, video, and text data—encompassing 1 billion text tokens, 10 billion audio tokens, and 1 trillion video tokens—let alone processing this data on-device.Our innovative team, consisting of PhD experts from the Stanford AI Lab, has pioneered State Space Models (SSMs) as a new foundation for training efficient, large-scale AI models. We pride ourselves on our deep expertise in model innovation and systems engineering, combined with a design-focused product engineering team that develops and delivers cutting-edge models and user experiences.Supported by prominent investors like Index Ventures and Lightspeed Venture Partners, alongside Factory, Conviction, A Star, General Catalyst, and SV Angel, we benefit from the insights of leading advisors and over 90 angels from various industries, including some of the most respected figures in AI.About the RoleWe are seeking an Enterprise Engineer to help propel our mission of creating real-time multimodal intelligence through the deployment of agile voice AI solutions for our customers.Your ImpactDesign and construct enterprise-grade systems, including On-Premise Deployments and Agent Infrastructure.Take ownership of creating and implementing robust platform capabilities tailored to enterprise requirements—focusing on the abstractions, core modifications, and infrastructure that support Cartesia's largest clients.Transform recurring deployment patterns (including gaps, incident themes, and evaluation results) from temporary solutions into scalable, long-term platform features.Establish and elevate standards for reliability, security, and operational excellence across Cartesia's enterprise interface.You will have substantial responsibility over core capabilities that will determine Cartesia's scalability within the most challenging enterprise environments worldwide.What You BringSolid backend engineering expertise—you have designed and implemented infrastructure, platform services, or foundational abstractions utilized by other teams.Proficiency in Go and/or Python programming languages.You prioritize long-term maintainability in your design and coding practices.

About CartesiaAt Cartesia, we are on a mission to create the next generation of artificial intelligence—smart, interactive systems that function seamlessly in any environment. Currently, the most advanced models struggle to process and analyze extensive streams of audio, video, and text over extended periods—1 billion text tokens, 10 billion audio tokens, and 1 trillion video tokens—especially when integrated directly on devices.We are at the forefront of developing the model architectures that will enable this innovation. Our founding team, which originated from the Stanford AI Lab, is responsible for the creation of State Space Models (SSMs), a groundbreaking approach for training efficient, large-scale foundational models. Our team merges deep technical knowledge in model development and systems engineering with a product engineering group focused on design, allowing us to create and deliver pioneering models and user experiences.Supported by top-tier investors such as Index Ventures, Lightspeed Venture Partners, and others, along with guidance from industry-leading advisors and over 90 angel investors, we are well-equipped to reshape the landscape of AI.About the RoleWe are seeking a skilled Software Engineer to join our team and help propel our vision of real-time, multimodal intelligence.Your ImpactDevelop and implement a low-latency, scalable, and dependable model inference and serving framework for our innovative SSM foundational models.Collaborate with our research and product engineering teams to translate cutting-edge research into extraordinary products.Establish robust, high-quality data processing and evaluation infrastructure for training foundational models.Enjoy significant autonomy in shaping our product direction and influencing how advanced AI technologies are utilized across various devices and applications.What You BringGiven the complexity of the challenges we tackle, we prioritize strong engineering capabilities at Cartesia.Proficient engineering skills with the ability to navigate intricate codebases and monorepos.A keen eye for detail, ensuring the production of clean, maintainable code.Adaptability to new technologies and quick proficiency with our tech stack, which includes Go and Python for backend development and Next.js for frontend.Experience in building large-scale distributed systems that require high performance, reliability, and observability.

About CartesiaAt Cartesia, we are on a mission to revolutionize artificial intelligence by creating interactive, ubiquitous intelligence that operates seamlessly in any environment. Our vision includes pushing the boundaries of current AI capabilities, enabling models to continuously process and reason over vast streams of audio, video, and text data—1 billion text tokens, 10 billion audio tokens, and 1 trillion video tokens—on-device.Our pioneering work in model architectures originates from our founding team’s experience at the Stanford AI Lab, where we developed State Space Models (SSMs), a breakthrough approach for training large-scale, efficient foundation models. Our team is a blend of deep expertise in model innovation and systems engineering, combined with a design-focused product engineering team dedicated to launching cutting-edge models and user experiences.Backed by top-tier investors including Index Ventures and Lightspeed Venture Partners, alongside a robust network of advisors and over 90 angel investors from various sectors, we are fortunate to collaborate with some of the leading minds in AI.About the RoleWe are excited to welcome our first Solutions Engineer, who will play a vital role in facilitating the enterprise adoption of Cartesia’s voice AI infrastructure. Our clients are developing real-time voice agents, call automation systems, and AI workflows that rely on low latency, reliability, and seamless production-grade integration.As a Solutions Engineer, you will collaborate closely with Account Executives throughout the technical aspects of key deals—from initial discovery to proof-of-concept and technical validation. You will bridge the gap between engineering and market entry, translating customer workflows and infrastructure challenges into actionable architectural solutions.This role demands a proactive, hands-on approach. You will write code, create demos, prototype integrations, and engage in technical discussions with engineering leaders. Rather than following an existing playbook, you'll contribute to developing one by establishing demo environments, documentation, and scalable processes as we expand.Your contributions as a Solutions Engineer will be crucial for our growth; deals will be secured because of sound architecture, functional integration, and the trust we build with customers to power their real-time production systems.

About CartesiaAt Cartesia, our vision is to create the future of artificial intelligence—intelligent systems that are seamlessly integrated into daily life. We aim to overcome current limitations by enabling models to continuously understand and analyze vast streams of audio, video, and text data—ranging from 1 billion text tokens to 1 trillion video tokens—right on your device.Our pioneering team, comprised of PhDs from the Stanford AI Lab, has developed State Space Models (SSMs), a groundbreaking approach to training efficient, large-scale foundation models. With a rich blend of expertise in model innovation and systems engineering, alongside a product-focused engineering team, we are committed to developing and delivering cutting-edge AI models and user experiences.Supported by prominent investors including Index Ventures and Lightspeed Venture Partners, as well as many esteemed advisors and over 90 angel investors from diverse industries, we are at the forefront of AI advancements.About The RoleIn our quest to create truly global AI, we must train our models using datasets that represent the vast diversity of languages and cultures around the world. We are looking for a Research Engineer to take charge of the quality and comprehensiveness of the data that drives our models. As our in-house expert in global data, you will ensure that our models excel across multiple languages, leveraging your keen understanding of linguistic subtleties and your enthusiasm for building inclusive, large-scale datasets.Your ImpactDesign and construct extensive datasets for model training, conducting controlled experiments to evaluate their effect on model performance.Develop assessments for speech models through both manual annotation and automated evaluation metrics.Utilize data generation techniques to enhance model intelligence and reduce biases.Create automated quality control systems to validate and filter the generated data.Collaborate with product teams to ensure optimal support for key languages and markets.What You BringProven experience in developing or working with extensive multilingual datasets.Familiarity with generative models, including speech, text, or multimodal systems.Ability to guide human annotation and evaluation across various languages.Strong analytical skills and a passion for data-driven decision-making.

About CartesiaAt Cartesia, our vision is to create the next generation of AI: an interactive intelligence that can operate seamlessly across various environments. Currently, no existing models can continuously process and reason over extensive streams of audio, video, and text—1B text tokens, 10B audio tokens, and 1T video tokens—especially not on-device.We are at the forefront of pioneering model architectures that make this vision a reality. Our founding team, comprised of PhDs from the Stanford AI Lab, invented State Space Models (SSMs), a groundbreaking approach for training efficient, large-scale foundation models. Our team melds deep expertise in model innovation and systems engineering with a design-focused product engineering team, committed to developing and delivering state-of-the-art models and user experiences.Supported by top investors such as Index Ventures and Lightspeed Venture Partners, along with Factory, Conviction, A Star, General Catalyst, SV Angel, Databricks, and a host of exceptional advisors and over 90 angels across diverse industries, we are privileged to collaborate with some of the leading experts in AI.About the RoleWe are seeking a dynamic Product Engineer, Surfaces to join our team. In this role, you will be instrumental in delivering high-quality, model-driven experiences across all of Cartesia’s surfaces—including web, SDKs, documentation, and APIs—while collaborating closely with our go-to-market, model serving, research, and product teams.Your ImpactDevelop and ship developer-centric products by engaging with users and employing first-principles thinking.Introduce Cartesia’s cutting-edge models to the market by building high-performance interfaces for customer access.Implement rigorous evaluation metrics to assess the impact of your work and refine it based on user feedback.Work collaboratively with cross-functional teams to create surfaces that enhance Cartesia’s growth and amplify our collective output.What You BringA minimum of 2 years of experience in full-stack development.Proficiency in TypeScript, with hands-on experience in building modern web applications using React.A strong intuition regarding the components of an excellent developer experience.Backend development skills in Python or Go, emphasizing API design.Demonstrated success in delivering and iterating on a user-facing product in a fast-paced environment.

About CartesiaAt Cartesia, we are on a mission to revolutionize artificial intelligence by creating interactive intelligence that is seamlessly integrated into everyday life. Our innovative approach is focused on developing models that can process and reason over extensive streams of audio, video, and text, enabling real-time, on-device capabilities.Our founding team, comprised of PhDs from the Stanford AI Lab, has pioneered State Space Models (SSMs), a groundbreaking method for training efficient, large-scale foundation models. With a blend of model innovation and systems engineering expertise, coupled with a design-oriented product engineering team, we are dedicated to delivering state-of-the-art models and user experiences.We are backed by top investors such as Index Ventures and Lightspeed Venture Partners, and supported by a network of esteemed advisors and over 90 angel investors from various industries, including some of the leading experts in AI.About the RoleWe are seeking a Forward Deployed Engineer to propel our mission of developing real-time, multimodal intelligence. In this role, you will work closely with enterprise customers to implement voice AI solutions directly into their production environments. As an FDE, you will enhance customer success and drive revenue by transforming Cartesia's core product into impactful solutions.Your ImpactWrite and ship production-grade code – Create, build, and deploy voice AI systems that enhance real enterprise workflows.Own deployments end-to-end – Lead the discovery, architecture, implementation, and rollout for key customer engagements, demonstrating your ability to navigate ambiguity and drive project progress.Deliver across complex infrastructure – Manage deployments in cloud, VPC, and on-prem environments while ensuring compliance with security and networking requirements.Unblock critical integrations – Identify and resolve integration challenges, performance issues, and deployment obstacles under real-world constraints.Drive expansion through building – Discover new use cases and prototype solutions that enhance customer adoption and long-term value.

About CartesiaAt Cartesia, we are on a mission to revolutionize artificial intelligence by creating interactive intelligence that is accessible and effective in any environment. We have identified a gap in current AI capabilities; existing models struggle to continuously process extensive streams of audio, video, and text data. Our vision is to bridge this gap by developing pioneering model architectures.Founded by PhD experts from the Stanford AI Lab, we are the creators of State Space Models (SSMs), a groundbreaking approach to training efficient, large-scale foundation models. Our team merges profound expertise in model innovation with systems engineering and product design to deliver advanced models and user experiences.Backed by leading investors such as Index Ventures and Lightspeed Venture Partners, along with an array of esteemed advisors, we are well-positioned to push the boundaries of AI.About the RoleWe are seeking a talented Software Engineer specializing in database systems to architect and scale Cartesia’s data infrastructure. You will play a crucial role in implementing robust data governance and developing user-friendly, secure database tools that empower both engineers and non-engineers.Your ImpactDesign and enhance database platforms to ensure scalability to over 100 times current capacity while maintaining uptime, latency, and accuracy.Construct data storage architectures that function seamlessly across various environments including AWS, GCP, on-premises systems, and third-party deployments.Facilitate accelerated development across the organization by providing high-quality database tools and resources to both technical and non-technical users.Implement secure access control mechanisms to ensure sensitive data is restricted to authorized personnel only.Develop scalable data governance systems focused on permissions, auditing, and compliance, utilizing IAM policies, ACLs, and security controls across a large user base.What You BringExpertise with cloud services such as AWS, GCP, or Azure, along with experience using infrastructure-as-code tools like Terraform.A proven history of managing database systems during periods of rapid growth in dynamic environments.

Join Cartesia as a Technical Recruiter!At Cartesia, we are on a mission to revolutionize artificial intelligence by creating interactive intelligence systems capable of processing extensive streams of audio, video, and text on-device. Our innovative approach is rooted in the groundbreaking work of our founding team at the Stanford AI Lab, where we developed State Space Models (SSMs) that empower large-scale foundation models.Backed by top investors including Index Ventures and Lightspeed Venture Partners, our team is composed of industry-leading experts in AI, engineering, and product design. Join us as we shape the future of AI!Your RoleAs a Technical Recruiter at Cartesia, you will play a pivotal role in expanding our talented team of engineers and researchers. You will manage the complete hiring process for technical positions, collaborating closely with hiring managers to craft exceptional talent pipelines. This high-impact role will allow you to influence our team dynamics and contribute to our vibrant company culture.Key ResponsibilitiesOversee end-to-end recruitment for technical roles in engineering and research.Work with hiring managers to establish role requirements and develop effective interview strategies.Cultivate diverse talent pipelines through innovative sourcing techniques and outreach initiatives.Create engaging outreach messages that reflect Cartesia's mission and values.Facilitate a respectful and efficient interview process for all candidates.Monitor and report on recruitment metrics and pipeline health, suggesting improvements as needed.Enhance recruiting operations, tools, and best practices.Support employer branding efforts and strategic hiring initiatives.

About CartesiaAt Cartesia, we are on a mission to revolutionize artificial intelligence by creating interactive, ubiquitous intelligence that operates seamlessly wherever you are. Current AI models struggle to continuously process and reason over extensive streams of data, including a year’s worth of audio, video, and text. Our innovative team is developing advanced model architectures to overcome these challenges.Founded by PhDs from the Stanford AI Lab who pioneered State Space Models, we blend deep expertise in model innovation with a design-focused engineering approach. With backing from top-tier investors such as Index Ventures and Lightspeed Venture Partners, along with a network of industry-leading advisors, we are pushing the boundaries of AI.About the RoleJoin our New Horizons Evaluations team as the Evaluations Lead, where you will redefine how we measure progress in interactive machine intelligence. You will create evaluation frameworks that assess not only what models know but also how they reason, remember, and engage over time. This multifaceted role bridges research, product development, and infrastructure to establish metrics and systems that articulate the essence of “intelligence” in the next wave of AI. Ideal candidates will possess a blend of scientific rigor and technical prowess, alongside a genuine curiosity about user interactions with intelligent systems. Your contributions will be pivotal in shaping Cartesia’s model development, focusing on deeper qualities such as understanding, naturalness, and adaptability in real-world applications.Your ImpactDefine and identify essential model capabilities and behaviors for next-generation evaluations.Develop and implement comprehensive evaluation pipelines with robust statistical analysis and transparent reporting.Collaborate closely with model training and research teams to integrate evaluation systems into the model development process.Design and prototype user studies and behavioral experiments to ground evaluations in practical use.

Join Cartesia: Pioneering AI InnovationAt Cartesia, we are on a mission to redefine the landscape of artificial intelligence. Our goal is to create the next generation of AI that is interactive, ubiquitous, and capable of continuous reasoning across vast streams of audio, video, and text data. With an impressive foundation built on our pioneering work in State Space Models (SSMs) at the Stanford AI Lab, our team is uniquely positioned to advance model architectures that will make on-device reasoning a reality.Backed by prominent investors like Index Ventures and Lightspeed Venture Partners, along with a network of 90+ advisors, including top experts in AI, we are committed to pushing the boundaries of model innovation and systems engineering.About the RoleWe believe that the next significant advancement in model intelligence will stem from enhanced post-training methods and alignment strategies. As a Post-Training Researcher, you will be at the forefront of developing systems and methodologies that ensure our multimodal models are not just adaptive, but also aligned with human intentions.In this role, you will collaborate across machine learning research, alignment, and infrastructure, crafting innovative techniques for preference optimization, model evaluation, and feedback-driven learning. You will investigate how feedback signals can enhance reasoning capabilities across various modalities while establishing the necessary infrastructure to scale and improve these processes.Your contributions will be pivotal in shaping the learning and improvement trajectory of Cartesia’s foundational models, ultimately enhancing their connection with users.Your ImpactLead research initiatives aimed at enhancing the capabilities and alignment of multimodal models.Create cutting-edge post-training methods and evaluation frameworks to assess model advancements.Collaborate closely with research, product, and platform teams to establish best practices for specialized model development.Design, debug, and scale experimental systems to ensure reliability and reproducibility throughout training cycles.Convert research insights into production-ready systems that enhance model reasoning, consistency, and alignment with human values.

About CartesiaAt Cartesia, we're on a mission to create the future of AI: a seamless, interactive intelligence that operates wherever you are. Currently, even the most advanced models struggle to continuously analyze and reason over extensive streams of audio, video, and text—spanning 1 billion text tokens, 10 billion audio tokens, and 1 trillion video tokens—especially on-device.We are at the forefront of developing the model architectures that will change this landscape. Our founding team, comprised of PhDs from the Stanford AI Lab, invented State Space Models (SSMs), a groundbreaking approach for training efficient, large-scale foundation models. Our team merges deep expertise in model innovation and systems engineering with a design-centric product engineering focus to develop and launch cutting-edge models and user experiences.Supported by top-tier investors such as Index Ventures and Lightspeed Venture Partners, along with Factory, Conviction, A Star, General Catalyst, SV Angel, and Databricks, we are grateful for the guidance of exceptional advisors and over 90 angel investors from diverse sectors, including the leading experts in AI.About the RoleWe are seeking a talented Design Engineer to enhance our React design systems and elevate the quality of our web interfaces.Your ImpactTake ownership of the visual aspects of our web surfaces, proactively identifying and resolving design and performance issues.Create and implement UI features from the ground up.Focus on fine-tuning every detail, ensuring pixel-perfect designs.Develop and maintain a React design system to significantly enhance product engineering efficiency.Establish processes that allow Cartesia to proactively identify design gaps and opportunities for improvement on our web platforms.What You BringA minimum of 2 years of relevant experience.A strong proficiency in both design and engineering disciplines.A keen eye for pixel-level details and imperfections in digital interfaces.Expertise in TypeScript, with a commitment to writing clean, maintainable code.A portfolio showcasing your design engineering work (website or social profile).A perfectionist approach towards quality fundamentals: meticulous polish, clear copy, accessibility, and web performance.Experience in developing and managing React-based design systems.

Role Overview Cartesia is seeking a contract Data Quality Operations Analyst to join the team at its San Francisco headquarters. This position plays a central part in maintaining accurate and reliable data across company operations. What You Will Do Monitor and uphold data integrity throughout different operational areas Work closely with teams across the company to spot and resolve data discrepancies Develop and refine processes that improve data quality Apply analytical skills to support data-driven decisions within the organization Location San Francisco, CA (Headquarters)

About CartesiaAt Cartesia, we are on a mission to revolutionize artificial intelligence by creating a seamless, interactive intelligence that is accessible wherever you are. Our pioneering efforts focus on developing model architectures capable of processing extensive streams of audio, video, and text—surpassing current capabilities of even the best existing models.Our founding team, comprised of PhDs from the Stanford AI Lab, invented State Space Models (SSMs)—a groundbreaking approach for training efficient, large-scale foundation models. We combine deep expertise in model innovation and systems engineering with a design-driven product engineering team to deliver cutting-edge models and exceptional user experiences.Backed by renowned investors such as Index Ventures and Lightspeed Venture Partners, as well as Factory, Conviction, A Star, General Catalyst, SV Angel, and Databricks, we have the support of numerous distinguished advisors and over 90 angel investors from various industries, including leading experts in AI.About the RoleWe are seeking a proactive Account Executive to enhance our sales initiatives and scale our sales operations. As an integral member of our early Go-To-Market (GTM) team, you will oversee a robust sales cycle—from prospecting and discovery to negotiation and closure—focusing on converting product-led growth leads and securing mid-market accounts.Your Impact:Manage the entire sales process for active opportunities: prospect, qualify, conduct discovery, build business cases, and close deals with urgency and precision.Generate a high-volume pipeline through a combination of PLG conversion, automated outbound prospecting programs, and inbound follow-up to consistently meet monthly and quarterly goals.Establish and nurture relationships with mid-market accounts, driving swift adoption and identifying expansion opportunities.Partner with Customer Success to grow key customers within the segment who are approaching contractual limits or have additional use cases.Build rapport with business buyers, department heads, and VPs by understanding their workflows, pain points, and ROI drivers amid fast-paced sales cycles.Collaborate closely with founders to refine our mid-market sales playbook, outbound strategies, pricing models, and customer engagement practices.

About CartesiaAt Cartesia, we are on a mission to redefine the future of artificial intelligence by creating ubiquitous, interactive intelligence that adapts to your environment. Our groundbreaking research has revealed that even the most advanced AI models currently struggle to process and reason over extensive streams of audio, video, and text—1B text tokens, 10B audio tokens, and 1T video tokens—especially in real-time on-device.Our founding team, consisting of PhDs from the Stanford AI Lab, pioneered State Space Models (SSMs), a crucial innovation for training efficient, large-scale foundational models. With a blend of deep expertise in model innovation and systems engineering, coupled with a design-focused product engineering team, we are dedicated to building and delivering state-of-the-art models and user experiences.Supported by esteemed investors like Index Ventures and Lightspeed Venture Partners, alongside Factory, Conviction, A Star, General Catalyst, SV Angel, and Databricks, we are privileged to collaborate with a remarkable group of advisors and over 90 angel investors across various sectors, including leading experts in AI.About the Role:We are seeking a Founding Product Marketer who will play a pivotal role in defining Cartesia's presence in the market. You will be instrumental in shaping our product launches, driving user adoption, and positioning us as the premier platform for developing voice agents. This is an exceptional opportunity to join us at the inception stage, building product marketing from the ground up in one of the most exciting domains of AI. You will be responsible for crafting our narrative and engaging with both developers and enterprises.The ideal candidate will possess a blend of strategic thinking and creativity. You will have the ability to distill complex technical ideas into clear, compelling stories while exploring innovative concepts, organic growth strategies, and community-driven initiatives. You will collaborate closely with the founders, Product, and Go-To-Market (GTM) teams, with opportunities for career advancement as we scale.Your Impact:Oversee and execute product launches, ensuring clarity around new features and updates for customers and the market.Collaborate with Product and GTM teams to translate technical features into compelling value propositions for developers and enterprises.Lead initiatives aimed at enhancing product adoption, including onboarding processes, in-product messaging, and user education materials.Produce high-quality marketing collateral such as website content, whitepapers, sales enablement resources, case studies, and blog articles.Establish and maintain customer personas, messaging frameworks, and positioning across all product offerings.

Join our dynamic team at Perplexity as an AI Inference Engineer, where you will be at the forefront of deploying cutting-edge machine learning models for real-time inference. Our tech stack includes Python, Rust, C++, PyTorch, Triton, CUDA, and Kubernetes, providing you with a chance to work on large-scale applications that make a real impact.Key ResponsibilitiesDesign and develop APIs for AI inference that cater to both internal and external stakeholders.Conduct benchmarking and identify bottlenecks within our inference stack to enhance performance.Ensure the reliability and observability of our systems while promptly addressing any outages.Investigate innovative research and implement optimizations for LLM inference.

About the RoleWe are seeking a talented Inference Engineering Manager to spearhead our AI Inference team at Perplexity. This is a remarkable opportunity to design and expand the infrastructure that drives Perplexity's innovative products and APIs, catering to millions of users with cutting-edge AI capabilities.You will take charge of the technical direction and implementation of our inference systems while cultivating and leading a high-caliber team of inference engineers. Our technology stack encompasses Python, PyTorch, Rust, C++, and Kubernetes. You will play a crucial role in architecting and scaling the large-scale deployment of machine learning models for Perplexity's Comet, Sonar, Search, and Deep Research products.Why Perplexity?Develop state-of-the-art systems that are among the fastest in the industry using leading-edge technology.Engage in high-impact work within a smaller team, enjoying considerable ownership and autonomy.Seize the chance to create infrastructure from the ground up instead of maintaining outdated systems.Work across the entire spectrum: minimizing costs, scaling traffic, and advancing the capabilities of inference.Make a significant impact on the technical roadmap and team culture at a rapidly expanding company.ResponsibilitiesLead and nurture a high-performing team of AI inference engineers.Develop APIs for AI inference utilized by both internal and external clients.Design and scale our inference infrastructure for enhanced reliability and efficiency.Benchmark and resolve bottlenecks across our inference stack.Drive large sparse/MoE model inference at rack scale, including sharding strategies for extensive models.Innovate by developing inference systems that support sparse attention and disaggregated pre-fill/decoding serving.Enhance the reliability and observability of our systems and lead incident response efforts.Make technical decisions regarding batching, throughput, latency, and GPU utilization.Collaborate with ML research teams on model optimization and deployment.Recruit, mentor, and develop engineering talent.Establish team processes, engineering standards, and operational excellence.Qualifications5+ years of engineering experience, with at least 2 years in a technical leadership or management capacity.Proficiency in programming languages and tools such as Python, PyTorch, Rust, and C++.Experience with Kubernetes and cloud infrastructure.Strong understanding of machine learning model deployment and optimization.Exceptional problem-solving and communication skills.

Join the Fluidstack TeamAt Fluidstack, we’re pioneering the infrastructure for advanced intelligence. We collaborate with leading AI laboratories, governmental entities, and major corporations—including Mistral, Poolside, and Meta—to deliver computing solutions at unprecedented speeds.Our mission is to transform the vision of Artificial General Intelligence (AGI) into a reality. Driven by our purpose, our dedicated team is committed to building state-of-the-art infrastructure that prioritizes our customers' success. If you share our passion for excellence and are eager to contribute to the future of intelligence, we invite you to be part of our journey.Role OverviewThe Inference Platform team at Fluidstack is at the forefront of addressing the cost and latency challenges associated with frontier AI. You will play a crucial role in managing the serving layer that connects our global accelerator supply with the production workloads of our clients, which include LLM serving frameworks, KV cache infrastructure, and Kubernetes orchestration across multiple data centers.This hands-on individual contributor role combines elements of distributed systems, model optimization, and serving infrastructure. You will oversee the entire lifecycle of inference deployments for leading AI labs, striving for enhancements in throughput, cost-efficiency, and response times, while also influencing the architectural decisions that guide Fluidstack’s deployment strategies.

Baseten develops infrastructure and tools that help AI companies deploy and scale inference. Teams at organizations like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer rely on Baseten to bring advanced machine learning models into production. The company recently secured a $300M Series E from investors including BOND, IVP, Spark Capital, Greylock, and Conviction. Role overview This Software Engineer - GPU Inference position joins the founding team for Baseten Voice AI in San Francisco. The team focuses on building production-ready Voice AI systems, bringing open-source voice models into real-world use for clients in productivity, customer service, healthcare conversations, and education. The work shapes how people interact with technology through voice, creating broad impact across industries. In this role, the engineer leads the internal inference stack that powers Voice AI models. Responsibilities include guiding the product roadmap and driving engineering execution. Collaboration is a key part of the job, working closely with Forward Deployed Engineers, Model Performance Engineers, and other technical groups to advance Voice AI capabilities. Sample projects and initiatives The world's fastest Whisper, with streaming and diarization Canopy Labs selects Baseten for Orpheus TTS inference Partnering with the Core Product team to build an orchestration framework for a multi-model voice agent Working with the Training Platform team to support continuous training of voice models Designing a developer-friendly API and SDK for self-service adoption of Baseten Voice AI products