Senior Developer

WHAT YOU WILL OWN 

Features across the agent runtime, RAG, memory, evaluation and the Studio, working inside a senior engineer's track. You will build the reference agents, the knowledge-base pipeline, the eval datasets and much of the pilot feedback work — the parts of the product where AI quality is decided. 

MUST HAVE 

• Strong Python with modern tooling (typing, Pydantic, async, pytest); can work in TypeScript / React when needed. 

• Hands-on with LLM APIs: tool / function calling, structured outputs, prompt iteration, token and cost awareness; has shipped at least one LLM-powered feature to real users. 

• Built a RAG pipeline or search feature: chunking, embeddings, a vector database, retrieval evaluation. 

• Comfortable with PostgreSQL and Redis; understands REST API design and event-driven basics. 

• Works with Docker, Git and CI daily; writes tests without being asked. 

• Curious and rigorous: reads model behaviour from traces, forms a hypothesis, tests it. 

GOOD TO HAVE 

• LangGraph or another agent framework. Temporal. Kubernetes. Experience building evaluation datasets or with LLM-as-judge. Prior work on enterprise integrations. 

RESPONSIBILITIES 

• Implement features end to end — API, data model, tests, telemetry — from a design agreed with your track lead. 

• Build and tune agents: prompts, tool schemas, structured outputs, routing rules; measure them with the eval harness rather than by feel. 

• Own the knowledge-base pipeline (ingestion, chunking, embedding, retrieval quality) and the memory features. 

• Turn pilot transcripts and traces into eval cases and fixes. 

• Contribute to the Studio (React / TypeScript) when your feature needs a UI.

MUST HAVE 

• Strong Python with modern tooling (typing, Pydantic, async, pytest); can work in TypeScript / React when needed. 

• Hands-on with LLM APIs: tool / function calling, structured outputs, prompt iteration, token and cost awareness; has shipped at least one LLM-powered feature to real users. 

• Built a RAG pipeline or search feature: chunking, embeddings, a vector database, retrieval evaluation. 

• Comfortable with PostgreSQL and Redis; understands REST API design and event-driven basics. 

• Works with Docker, Git and CI daily; writes tests without being asked. 

• Curious and rigorous: reads model behaviour from traces, forms a hypothesis, tests it.