About the job
About Flow Engineering
Flow Engineering is revolutionizing the way modern engineering organizations manage their requirements through an AI-native platform. Our technology empowers hardware teams to collaborate seamlessly with AI agents, accelerating the design, validation, and evolution of complex systems with unparalleled speed and precision.
Role Overview
We are on the lookout for experienced Full Stack Software Engineers to join our dynamic team at Flow. In this role, you will create innovative AI-driven features that enhance how teams draft, review, and manage requirements. You will be instrumental in integrating AI into the workflows of systems and domain engineers, transforming the way teams conceptualize their projects.
This position sits at the intersection of artificial intelligence, product development, and full-stack engineering, allowing you to take concepts from their initial prototype phase all the way to stable, observable features in a live production environment.
Your Responsibilities
Create and implement AI-enhanced functionalities, such as assisted requirement drafting, consistency checks, impact analysis, and intelligent suggestions for systems and domain engineers.
Develop agentic workflows that enable systems and domain engineers to explore designs, simulate modifications, and validate requirements effectively.
Assess and incorporate language models and related tools, focusing on reliability, latency, cost-effectiveness, and debuggability in a production setting.
Construct and maintain essential infrastructure, including data pipelines, evaluation tools, model management systems, and observability frameworks.
Engage across the entire stack—from backend integrations and APIs to simple UI components—to deliver comprehensive AI features, rather than just model endpoints.
Collaborate with product teams and customers to identify high-impact workflows, conduct experiments, and iterate quickly based on feedback and usage data.
Qualifications
A minimum of 5 years of experience in developing production software, including service design, testing, and operation at scale within cloud environments.
Direct experience with modern large language model (LLM) providers and tools (e.g., OpenAI, Anthropic, Hugging Face, vector stores, RAG patterns).
Understanding of prompt design, retrieval-augmented systems, evaluation methodologies, and safety/guardrail techniques.
Ability to analyze trade-offs between various models, architectures, and deployment strategies to make informed decisions.
Thrives in a fast-paced, high-ownership environment where experimentation and iteration are encouraged.
Our Technology Stack (AI-focused)
- ...

