About the job
About Flow Engineering
Flow Engineering is a pioneering AI-native requirements platform tailored for contemporary engineering organizations. Our innovative technology empowers hardware teams to engage collaboratively with AI agents, facilitating the design, validation, and evolution of complex systems with unparalleled speed and precision.
About the Role
We are on the lookout for skilled staff software engineers with a focus on AI who are passionate about developing AI-infused capabilities. Your work will enhance how teams draft, review, and manage requirements efficiently. You will be integral to workflows involving agentic systems engineers and domain engineers, effectively placing AI at the core of team interactions and decision-making processes.
This position merges AI, product development, and full-stack engineering, enabling you to advance concepts from initial prototypes to robust, observable features in a production environment.
Key Responsibilities
Design and implement AI-enhanced functionalities such as assisted requirement drafting, consistency checks, impact assessments, and intelligent recommendations for systems and domain engineers.
Create agentic workflows that empower systems engineers and domain engineers to explore designs, simulate modifications, and validate requirements effectively.
Assess and incorporate language models and related tools, optimizing for reliability, latency, cost-effectiveness, and debuggability in production settings.
Develop and sustain the complementary infrastructure, including data pipelines, evaluation frameworks, prompt and model management, observability, as well as safety measures and guardrails.
Engage across the technology stack, from backend integrations and API development to user interface components, delivering comprehensive AI capabilities beyond mere model endpoints.
Collaborate with product teams and clients to pinpoint high-impact workflows, conduct experiments, and iterate swiftly based on user feedback.
Qualifications
A minimum of 3 years of experience in applied machine learning, large language models (LLMs), or related domains, with a proven history of deploying ML/LLM-driven features in live environments.
At least 8 years of experience in software development, including the design, testing, and operation of scalable services in a cloud-based infrastructure.
Proficiency with contemporary LLM providers and tools (e.g., OpenAI, Anthropic, Hugging Face, vector databases, retrieval-augmented generation patterns).
Familiarity with prompt crafting, retrieval-augmented systems, evaluation techniques, and safety protocols.
Strong analytical skills to evaluate trade-offs among various models, architectures, and deployment strategies, enabling pragmatic decision-making.
An openness to continuous learning and adapting to evolving technologies.
