Key Responsibilities

• Design and build LLM-powered backend services/APIs (Python, FastAPI preferred)
• Design robust workflows with tool/function calling, retries, fallbacks, and guardrails
• Implement structured outputs with strong validation and schema-driven contracts
• Develop and maintain RAG pipelines with retrieval, ranking, and generation
• Write high-quality unit and integration tests, including LLM behavior regression tests
• Containerize and deploy services across dev/stage/prod environments
• Collaborate closely with product and engineering teams to ship iteratively
• Contribute to clean documentation, runbooks, and API contracts

Must-Have

• Strong Python and backend engineering fundamentals
• Experience with FastAPI (or similar) and RESTful API design
• Hands-on LLM integration experience (OpenAI, Anthropic, Azure OpenAI, etc.)
• Solid testing practices (pytest, mocking, integration tests)
• Working knowledge of Docker, Git, and CI pipelines

Good-to-Have

• Experience with vector databases and embeddings (FAISS, Pinecone, pgvector, etc.)
• Exposure to observability (logging, metrics, tracing)
• Cloud experience (AWS/Azure/GCP)
• Familiarity with async workflows and background job patterns
• Experience with TypeScript/React