Software Engineer, Agent Studio

ABOUT THE ROLE:As an AI Engineer at Varick, you will take charge of designing and optimizing the intelligence layer within our enterprise operations. This involves creating agent systems that efficiently handle thousands of transactions, make classification decisions, and learn from human interactions.This position is suited for engineers with extensive experience in LLMs, agent architectures, and evaluation systems. You have successfully developed agent workflows that operate in production, not merely in demo environments. Your expertise includes prompt engineering, retrieval, tool calling, multi-agent orchestration, and the evaluation frameworks necessary for deploying trustworthy AI systems in enterprise settings.WHAT YOU'LL DO:• Design and implement agent architectures that tackle complex enterprise workflows, focusing on multi-step reasoning, tool calling, and exception handling.• Develop and sustain evaluation systems that ensure agent quality, accuracy, safety, and groundedness.• Create robust prompt systems, retrieval pipelines, and context engineering strategies to ensure reliable agent performance.• Establish feedback loops that empower agents to learn from human corrections and enhance their functionality over time.• Optimize inference costs and latency for production workloads to ensure efficiency.• Define and uphold best practices for agent reliability, observability, and governance.• Stay updated with the latest models, frameworks, and research to ensure impactful deployments into production.WHAT WE'RE LOOKING FOR:• At least 3 years of software engineering experience, with a minimum of 1–2 years dedicated to LLM applications or AI systems in a production environment.• Practical experience in constructing agent workflows featuring tool calling, retrieval, and multi-step reasoning.• A profound understanding of prompt engineering, context engineering, and methods to elicit reliable behavior from LLMs.• Experience in developing evaluation systems to assess AI output quality.• Proficient in Python with a solid foundation in backend engineering principles.• You have delivered AI features to actual users and have navigated challenges such as hallucinations, edge cases, accuracy drops, and cost management.• Must be based in San Francisco.

ABOUT THE ROLE:As a Full Stack Engineer at Varick Agents, you will play a pivotal role in developing the foundational infrastructure and product interfaces that drive our agent deployments. While this position is not client-facing, your contributions will ensure that each deployment is executed with enhanced speed, reliability, and consistency.This dynamic role requires you to engage with backend services, APIs, data pipelines, and user interfaces. Your responsibilities will include creating the orchestration layer for agent execution and developing the dashboards and controls utilized by clients, ensuring that every line of code you write supports real enterprise operations.WHAT YOU'LL DO:Develop and manage backend services for agent orchestration, tool activation, and workflow execution.Design and implement product interfaces for agent monitoring, human-in-the-loop controls, and client dashboards.Construct data pipelines that integrate with various enterprise systems such as ERPs, CRMs, and data warehouses.Create internal tools that expedite deployment processes and minimize engineering time for individual clients.Ensure the reliability, observability, and performance of production systems.Collaborate closely with Frontend Developers to transform client-specific solutions into reusable platform capabilities.WHAT WE'RE LOOKING FOR:At least 3 years of experience in software engineering, specifically in building production systems.Strong understanding of backend fundamentals including APIs, databases, cloud infrastructure, and distributed systems.Proficiency in full stack development, capable of creating both backend services and the UI that interfaces with them.Production experience with Python.Familiarity with cloud infrastructures such as AWS, GCP, or Azure, including containers, managed databases, and CI/CD practices.A commitment to code quality, testing, and the deployment of stable solutions.HELPFUL EXPERIENCE:Experience integrating with enterprise systems (REST/SOAP APIs, webhooks, ETL pipelines).Knowledge of large language model APIs and agent frameworks.Frontend development experience with technologies like React or Next.js.Experience with Infrastructure as Code tools like Terraform or Pulumi.Background in building multi-tenant SaaS or platform products.Experience in startup or early-stage environments.WHY VARICK:Join an innovative team at Varick Agents where you can make a significant impact through your engineering expertise.

About UsAt Sierra, we are revolutionizing customer interactions by harnessing the power of AI to create more human-centric business experiences. Headquartered in the vibrant city of San Francisco, our reach extends globally with offices in Atlanta, New York, London, France, Singapore, and Japan.Our company culture is built on core values that drive our mission: Trust, Customer Obsession, Craftsmanship, Intensity, and Family. These principles guide our operations and foster a collaborative environment where innovation thrives.Founded by industry visionaries Bret Taylor and Clay Bavor, Sierra is positioned at the forefront of AI technology. Bret’s impressive background includes serving as Board Chair of OpenAI and co-CEO of Salesforce, while Clay’s expertise stems from 18 years at Google, leading groundbreaking projects in AR/VR and Google Workspace.Your RoleDevelop and Deploy Cutting-Edge AI Agents: You will design and launch high-performance, reliable AI agents that are essential for driving revenue and enhancing customer experiences. These systems are not mere prototypes; they are robust solutions actively utilized across diverse sectors including finance, healthcare, and commerce.Lead the Agent Development Lifecycle: You will oversee the entire lifecycle of AI agents, from initial conception to deployment and ongoing optimization. Your role encompasses building, fine-tuning, and evolving these agents, while setting the standard for best practices in the Agent Development Life Cycle.Collaborate with Industry Leaders: Engage directly with executives from major enterprises to tackle their most critical challenges and create transformative AI solutions. You will also collaborate with innovative startups in Silicon Valley, integrating cutting-edge technology to enhance operational efficiency.

About the RoleIn this pivotal position, you will spearhead the complete development of our core agentic workflow engine and Copilot—an innovative AI assistant designed to facilitate developers in creating and troubleshooting workflows through natural language, transforming abstract intentions into actionable, dependable agents. This role encompasses our backend (Next.js), orchestration layer, and all integrations with LLMs and external APIs.As the current leading tool for constructing workflows using natural language, your mission is to preserve and enhance its status—ensuring it remains swift, reliable, and adept at managing increasingly intricate agentic architectures.This foundational role allows you to establish architectural decisions, reliability benchmarks, and coding patterns that will define the functionality of our core product. Collaborating within a team of five, your contributions will be deployed to tens of thousands of developers on rapid release cycles.What You'll DoTake ownership of the agentic workflow engine: the runtime responsible for executing multi-step, tool-utilizing agent workflows in production.Develop and enhance Copilot—our natural language interface for creating, modifying, and debugging workflows.Design and sustain integrations with LLM providers (OpenAI, Anthropic, Google, local models via Ollama) and external APIs.Architect the orchestration layer that transforms visual flows into reliable, observable agent executions.Establish technical standards for the codebase—covering reliability, testing, code quality, and architectural patterns.Engage across the stack in our Next.js monorepo, delivering to production daily.Troubleshoot complex issues at the nexus of LLMs, distributed systems, and developer tooling.What We're Looking ForA capable generalist engineer with a history of deploying complex distributed systems or developer tools into production.Extensive experience with TypeScript/JavaScript and Bun; familiarity with working in a Next.js monorepo.Proven record of owning and managing production systems—you've been on call, debugged challenging issues, and ensured reliability.Experience integrating with LLMs or building upon foundational model APIs.Demonstrated high agency and ownership—within a small team, you help define the roadmap as much as you execute it.Strong architectural opinions that are adaptable—you prioritize building correctly while maintaining rapid development.Experience with AWS infrastructure is a plus.

Join Sierra as a Software Engineer specializing in Agent Architecture. In this role, you will be responsible for designing and developing innovative software solutions that empower our agents and enhance their capabilities. Collaborate with cross-functional teams to ensure seamless integration of our software with existing systems.

Why Choose Flux?At Flux, we are transforming the landscape of hardware development by pioneering the world's first AI Hardware Engineer. Our mission is to democratize access to cutting-edge hardware creation and transform the way electronics are designed and manufactured globally.About the RoleWe are on a quest to build the first AI Hardware Engineer, software capable of designing tangible, manufacturable electronics from simple prompts. As a Senior Software Engineer focusing on Agentic Development, you will be responsible for creating the system's intelligence, developing agentic workflows, reasoning graphs, and integrations that empower both novice and experienced engineers in their journey from concept to manufacturable hardware.This position fuses advanced web engineering with AI systems design. You will leverage TypeScript and LangGraph within the Flux web application and backend platform, embedding intelligent features directly into the design environment.Key ResponsibilitiesDevelop and implement agentic reasoning capabilities using TypeScript (LangGraph).Integrate AI functionalities into the Flux web application (React/Redux) and Chat UI.Implement telemetry and logging for monitoring runtime health, performance, and cost efficiency.Collaborate closely with product and electrical engineers to refine intelligent ECAD workflows.Conduct evaluations and translate insights into engineering decisions.Contribute to the development of agentic patterns, conventions, and best practices within the engineering organization.Required Qualifications8+ years of experience in software engineering, with at least 1 year in developing generative-AI or agentic systems.Proficient in TypeScript, React, and Node.js.Experience with LangChain, LangGraph, or similar orchestration frameworks.Proven track record in building asynchronous, distributed systems in a production environment.Experience in integrating LLM-based systems into complex user-facing web products.Strong communication skills and comfort working in a fully remote, asynchronous team setting.Previous experience in a startup or in 0→1 product development environments.Preferred QualificationsFamiliarity with retrieval systems, evaluation pipelines, or agent benchmarking.

About the TeamThe Codex Core Agent team is at the forefront of developing the foundational elements of Codex. Our mission is to enhance the agent's capabilities, expedite research efforts, and ensure these advancements are implemented effectively for our users.This involves collaborating across various systems that empower Codex to operate seamlessly in the real world. We focus on optimizing production performance metrics such as token management, latency, reliability, cost efficiency, and capacity. Our work encompasses the core execution loop and interfaces that translate models into actionable behaviors, as well as the shared infrastructure that supports other teams in leveraging Codex. Additionally, we establish feedback mechanisms that refine models and agent behaviors based on real-world usage over time.About the RoleWe are seeking passionate engineers to develop the infrastructure that fuels Codex agents in production environments. This role centers on the systems that ensure models can execute code securely, interact with various tools, complete complex, multi-step tasks, and maintain reliability and efficiency at scale.You will be responsible for designing and managing the infrastructure that supports sandboxed execution, orchestration, stateful workflows, application server and SDK boundaries, as well as model rollouts. Working at the intersection of distributed systems, developer tools, and AI, you will create the core components that enhance Codex's performance, safety, and reliability, making it easier for teams across the organization to build on its capabilities.What You’ll DoDesign and implement execution environments tailored for AI agents, incorporating features like sandboxing, isolation, and reproducibility.Develop orchestration systems for agents that handle multi-step processes and tool utilization.Create infrastructure for the execution, testing, and debugging of code generated by models.Establish state and memory systems that enable agents to maintain context during extended tasks.Optimize production metrics including tokens, latency, reliability, and cost across the Codex deployment.Assist in model rollouts, capacity planning, and managing the essential trade-offs between quality, speed, and cost to effectively handle a fleet of advanced agents at scale.Develop shared platform capabilities that facilitate the work of product teams, partner teams, and the open-source community contributing to Codex.You Might Be a Good Fit If YouPossess substantial experience in distributed systems or infrastructure engineering.Have experience building systems involving containers, sandboxing, or virtualization.Are adept at working across backend systems and collaborating with diverse teams to drive project success.

Join Decagon as a Staff Software Engineer specializing in Agent Development. In this pivotal role, you will work on cutting-edge software solutions that enhance our capabilities in agent-based systems. You will collaborate with cross-functional teams to design, develop, and implement innovative software applications that drive our mission forward.

About Our TeamThe Agent Infrastructure team at OpenAI is dedicated to developing advanced systems that facilitate the training and deployment of innovative AI agents, both for internal use and global accessibility. We collaborate closely with researchers to architect and scale environments that empower agentic models, allowing them to execute code, troubleshoot issues, and evolve as software engineers do. Our training environment operates at an unprecedented scale, offering the flexibility to simulate any operational context an agent might encounter.In addition, we are responsible for the core platform that powers the deployment and execution of agents in production. Our infrastructure supports groundbreaking products like Codex, Operator, the tool functionalities in ChatGPT, and future agentic innovations.Our team tackles some of the most intricate challenges in scaling agent capabilities, focusing on the infrastructure layer to ensure that OpenAI can train the most advanced models globally while enhancing the utility of our agentic products for users everywhere.About Your RoleAs a Software Engineer on the Agent Infrastructure Team, you will engage directly with both research and product teams at OpenAI. Your role will involve constructing and scaling systems to train sophisticated agentic models and developing the necessary platforms and integrations to deploy new agents to millions of users worldwide.You will be responsible for building new capabilities—establishing the infrastructure and integrations required to train increasingly complex agentic models—and rapidly scaling these innovations across some of the largest computing clusters globally. Furthermore, you will play a pivotal role in launching agentic products by building, maintaining, and scaling the production platform that supports all agents.We seek individuals with extensive experience in AI infrastructure who excel in collaborating with researchers to create high-performance systems at massive scale for unique applications.This position is available in San Francisco, CA or New York City, NY. We employ a hybrid work model, requiring three days in the office each week, and we offer relocation assistance for new hires.

About DecagonDecagon stands at the forefront of conversational AI, empowering brands to create unparalleled customer experiences. Our platform enables leading enterprises such as Avis Budget Group, Block’s Cash App, Square, Chime, Oura Health, and Hunter Douglas to deploy AI agents that facilitate personalized, engaging interactions across voice, chat, email, SMS, and beyond.We envision a world where customer interactions transcend traditional support tickets and hold music, fostering quicker resolutions, richer dialogues, and stronger relationships. Our esteemed investors, including a16z, Accel, Bain Capital Ventures, Coatue, and Index Ventures, share this vision and support our mission.As an in-office company, we are united by our commitment to excellence and rapid execution. Our core values — Just Get It Done, Invent What Customers Want, Winner’s Mindset, and The Polymath Principle — guide our collaborative work environment and team growth.About the TeamThe Agent Orchestration team is responsible for developing the foundational execution layer that drives every agent interaction. We create systems that coordinate model reasoning, assess agent behavior, and ensure reliability in real-world customer scenarios. Our focus on accuracy, dependability, and speed enables Decagon agents to plan, decide, and act effectively across millions of interactions.About the RoleAs a Senior Software Engineer on the Agent Orchestration team, you will design and develop systems that govern the performance of Decagon agents in real-world conditions. You will tackle complex challenges associated with distributed systems and lay the groundwork for enhancing agent performance, reliability, and quality.This role offers significant autonomy and the opportunity to make a direct impact on the architecture of one of the most sophisticated agent platforms globally.In this role, you will:Develop the execution engine that supports intelligent agents at scale.Design systems that synchronize model reasoning and actions while maintaining speed and accuracy.Enhance reliability through improved testing, observability, and safety measures.Establish foundations that enable teams to evaluate and enhance agent behavior safely and continuously.

About DecagonDecagon stands at the forefront of conversational AI technology, empowering brands to offer exceptional concierge-style customer experiences. Our innovative platform is trusted by industry leaders such as Avis Budget Group, Block’s Cash App and Square, Chime, Oura Health, and Hunter Douglas, enabling them to deploy AI agents that facilitate personalized and engaging interactions across various channels including voice, chat, email, and SMS.We envision a future where customer interactions are transformed from mundane support tickets and waiting on hold to swift resolutions, meaningful dialogues, and enriched relationships. Our commitment to this vision is supported by esteemed investors like a16z, Accel, Bain Capital Ventures, Coatue, and Index Ventures, among others.Based in San Francisco, we foster an in-office culture that prioritizes excellence and momentum. Our core values—Just Get It Done, Invent What Customers Want, Winner’s Mindset, and The Polymath Principle—guide our collaborative efforts and collective growth.About the TeamThe Agent Orchestration team is responsible for developing the fundamental execution layer that facilitates every agent interaction. Our systems are designed to orchestrate model reasoning, assess agent performance, and ensure consistent agent behavior in real-world customer scenarios.With a focus on accuracy, dependability, and speed, our work influences how Decagon agents strategize, decide, and implement actions during millions of interactions.About the RoleAs a Senior Software Engineer on the Agent Orchestration team, you will be pivotal in shaping the long-term architecture of Decagon’s agent platform. You will spearhead substantial, multi-quarter projects that define the functionality and scalability of our orchestration engine, enabling engineers across the organization to build effectively upon it.This position is ideal for individuals who excel in technical depth, possess the ability to influence cross-functional teams, and are passionate about developing robust, principled systems that endure. You will collaborate closely with teams in Research, Infrastructure, Product Engineering, and Agent Software Engineering to establish the standards and frameworks that uphold the reliability and intelligence of Decagon agents.In this role, you will:Take ownership of the architecture and ongoing evolution of Decagon's core execution engine for agents.Lead the design of systems that manage complex reasoning and action flows on a large scale.Enhance reliability, testing, and observability standards throughout the orchestration stack.

About the RoleHex Technologies is seeking experienced Senior and Staff-Level Fullstack Engineers who are passionate about contributing to our revolutionary Magic AI features.At Hex, we are dedicated to developing integrated AI functionalities that enhance and expedite analytics workflows. The potential here is extraordinary, and we are in a unique position to transform how individuals interpret and utilize data.In this position, you will spearhead the integration of AI-driven features into the Hex platform, collaborating closely with our Research Team for context and model prompting, as well as with other product engineering teams for seamless integration. Your efforts will significantly alter the data interaction experience for thousands of users, placing you at the forefront of one of the most exciting technological evolutions of our time. As a member of our Agent Platform Team, you will manage the scalable infrastructure that powers today's most advanced data agents and the innovative experimentation tools that enable rapid development of new AI features.

Transforming AI Through Self-ImprovementAt Letta, we are pioneering the development of self-improving artificial intelligence systems. Unlike traditional AI, which can be inflexible and limited, our agents are designed to learn continuously from their experiences and adapt accordingly.Founded by the innovators behind MemGPT at UC Berkeley’s Sky Computing Lab—the home of industry-changing technologies like Spark and Ray—Letta is supported by prominent figures in AI infrastructure, including Jeff Dean and Clem Delangue. Our agents are already making a difference in production environments for esteemed companies such as 11x and Bilt Rewards, evolving and enhancing their capabilities daily.We are forming a top-tier team of researchers and engineers to tackle AI's most significant challenge: creating machines that can reason, remember, and learn as humans do.Note: This position requires in-person attendance in our downtown San Francisco office, five days a week.

Join our innovative team at Pallet as a Forward Deployed Software Engineer specializing in AI Agents. In this pivotal role, you will develop and implement cutting-edge AI solutions that enhance user experiences and streamline operations. Collaborate with cross-functional teams to deliver impactful software that drives our mission forward.

Join Perplexity as a dynamic AI Software Engineer on our innovative Comet Agents engineering team. We are a tight-knit group of AI/ML specialists, backend developers, and full-stack engineers dedicated to creating engaging agentic experiences within our Comet ecosystem. Our mission is to empower users with AI agents that genuinely understand and fulfill their intents, enabling seamless, open-ended interactions with the digital world.As a key contributor to the Comet Agents team, you will apply your AI expertise, product intuition, and creative problem-solving skills to push the boundaries of what AI agents can achieve for our millions of loyal users. Your work will span applied research and engineering, tackling various challenges in AI, including:Crafting AI agents capable of navigating the digital landscape and executing valuable tasks for users;Developing action and decision models that effectively achieve user-defined objectives based on complex multimodal states;Delivering exceptional user experiences across desktop, mobile, headless cloud, and more, utilizing flexible abstractions and seamless background processes;Implementing secure-by-design capabilities through the creation of permission architectures and payload classifiers;Designing optimal data representations and interaction modes between agents and their environments;And much more!ResponsibilitiesLead the development of cutting-edge AI functionalities within our rapidly evolving AI agents product.Utilize advanced AI models, infrastructure, and browser technologies to enhance capabilities for our expanding user base.Uphold high standards of quality and performance in AI agents and user experience.Collaborate with engineers, designers, product managers, and data scientists to integrate core Perplexity functionalities into Comet agents.Contribute to product reliability, code quality, AI evaluation, testing, and ongoing maintenance across the team.QualificationsSolid foundational knowledge of the complete AI product stack.Experience with AI/ML frameworks and backend development.Proficiency in programming languages commonly used in AI development.Ability to work collaboratively in a fast-paced, interdisciplinary environment.Strong problem-solving skills and a passion for innovation in AI technologies.

Join Decagon as a Senior Software Engineer specializing in Agent Development. In this pivotal role, you will be responsible for designing, implementing, and optimizing software solutions that enhance our agent systems. You will collaborate with cross-functional teams to drive innovative projects, ensuring the highest quality and performance of our applications.

About Tenable:Tenable® is at the forefront of Exposure Management. With 44,000 organizations worldwide counting on us to mitigate cyber risk, we empower 65% of the Fortune 500, 45% of the Global 2000, and numerous governmental agencies. Join us in redefining the cybersecurity landscape!Why Choose Tenable?When you ask our team about what makes Tenable a fantastic workplace, the answer is simple: our people! Together, we innovate cutting-edge cybersecurity solutions, fostering a culture of inclusion, respect, and excellence. As part of the #OneTenable team, you'll collaborate with some of the industry's most talented professionals while having access to the resources necessary to make a meaningful impact. We strive to deliver exceptional results and celebrate our victories together!Note: Applicants must be authorized to work in the U.S. without sponsorship. We currently cannot sponsor work visas.Location: Must reside in or be willing to relocate to the San Francisco/San Jose area.Your Role:At Tenable, we're not just creating exceptional products; we're cultivating a premier engineering culture dedicated to hiring top talent. We are seeking a Senior Software Engineer to be part of a pioneering initiative within our engineering team. In this role, you will design and implement the Agentic AI Platform, an orchestration layer that empowers autonomous agents to reason, plan, and execute intricate security workflows within our Exposure Management ecosystem.This role is highly hands-on and has a significant impact. You won't merely be utilizing LLMs; you'll be constructing distributed systems, state machines, and tools that transform generative models into reliable, enterprise-grade agents.While this role is primarily remote, occasional in-person meetings may be necessary.Your Opportunity:Construct the Agentic Backbone: Design and implement backend services that facilitate multi-agent workflows, enabling AI agents to break down complex user requests, manage states, and execute tasks across distributed microservices....

ABOUT THE ROLE:As a Forward Deployed Engineer at Varick, you will play a pivotal hybrid role that merges engineering prowess with client engagement. You will collaborate directly with enterprise clients, akin to strategists, while also taking on the technical challenge of building solutions. Your responsibilities will include conducting audits, mapping workflows, identifying automation opportunities, and coding the solutions that bring those opportunities to life. You will be the vital link from the initial discovery phase through to deployment.This position demands an individual capable of engaging with C-suite executives, such as CFOs, to analyze their month-end closing processes and then architecting the necessary systems to enhance efficiency. The ideal candidate will possess both the polished client-facing skills and deep technical expertise, as we require a rare blend of both.

Coframe seeks Agent Engineers based in the SF Bay Area to design and build scalable systems focused on generating, testing, and monitoring user interfaces. This position centers on delivering reliable solutions that support a range of products and platforms. Key responsibilities Develop systems that create consistent, production-ready experiences for multiple platforms Implement automated tools for quality assurance and interface monitoring Enable rapid experimentation and ongoing optimization Role impact Agent Engineers at Coframe play a direct role in improving optimization, accelerating experimentation, and achieving measurable results across various products and platforms.