About the job
About Flow Engineering
Flow Engineering is an innovative platform harnessing the power of AI to transform how modern engineering teams manage requirements. Our AI-native solution empowers hardware teams to collaborate seamlessly with intelligent agents, facilitating the design, validation, and evolution of complex systems at unprecedented speed and precision.
About the Role
We are on the lookout for experienced senior software engineers with a passion for AI to develop advanced capabilities that enhance the way teams create, review, and oversee requirements. In this role, you will engage with agentic systems and domain engineer workflows, positioning AI at the core of team decision-making processes regarding their systems.
This position uniquely integrates AI, product development, and full-stack engineering, allowing you to transform ideas from initial prototypes into stable, observable features deployed in production environments.
What You’ll Do
Design and implement AI-driven features, such as assisted requirement drafting, consistency checks, impact analysis, and intelligent suggestions tailored for systems and domain engineers.
Create agentic workflows that empower systems engineers and domain engineers to explore designs, simulate changes, and validate requirements effectively.
Assess and integrate language models and associated tools, focusing on optimizing reliability, latency, cost, and debuggability within production settings.
Develop and sustain the necessary infrastructure, including data pipelines, evaluation harnesses, prompt and model management, observability, and safety protocols.
Engage across the entire technology stack—from backend integrations and APIs to user interface components—to deliver comprehensive AI features beyond mere model endpoints.
Collaborate with product teams and customers to identify high-value workflows, conduct experiments, and iterate rapidly based on real-world usage insights.
About You
A minimum of 3 years’ experience in applied machine learning, large language models, or related fields, with a proven history of delivering ML/LLM-powered features to production.
At least 5 years of experience in software development, involving the design, testing, and operation of scalable services in a cloud-based environment.
Practical experience with contemporary LLM providers and tools (e.g., OpenAI, Anthropic, Hugging Face, vector stores, and retrieval-augmented generation patterns).
Familiarity with prompt design, retrieval-augmented systems, evaluation methodologies, and safety/guardrail strategies.
Strong analytical skills to evaluate trade-offs between various models, architectures, and deployment patterns, enabling informed decision-making.
A collaborative spirit and effective communication skills to work alongside cross-functional teams.

