Python Engineer (Langgraph)

As Principal AI Engineer you are the technical owner of the AI core. You lead the audit of the existing codebase, define the architecture we evolve toward, build the test and evaluation harness that lets us ship changes safely, and you are the engineer who is paged when the AI surface misbehaves in production.

What you'll do

First 90 days

• Audit atlas-ai: agent flows, LangGraph state machines, Celery topology, datastore usage, OpenAI integration patterns
• Produce a written assessment of operational risk: failure modes, race conditions, retry semantics, idempotency, checkpoint integrity
• Quantify token cost per agent flow and per user session
• Identify the highest-risk subsystems and propose stabilisation plans
• Build (or harden) an evaluation harness for the agent flows — golden cases, regression suites, hallucination/safety tests
• Lead the knowledge-transfer sessions from the client's AI team

Ongoing

• Set the technical direction for the AI core
• Lead design for new agent flows and major changes to existing ones
• Own the production health of the AI surface (with platform/SRE support)
• Hire and mentor the rest of the AI squad (~10 engineers at full scale)
• Represent the AI core in cross-team architecture conversations with the client

Must-have skills

• 7+ years Python
• Deep LangGraph experience
• Strong LangChain ecosystem knowledge
• Production FastAPI — streaming responses, dependency injection, middleware, async patterns
• Celery + Redis broker in production
• Concurrency in Python — asyncio (gather, structured concurrency, cancellation), threading boundaries, mixing sync and async code safely
• Multi-datastore operations — MongoDB + Redis + Postgres
• OpenAI API at scale — rate limits, retries with exponential backoff, fallback model routing, streaming, tool/function calling
• Agent design patterns — ReAct, plan-and-execute, supervisor patterns, tool-use loops, multi-turn state, interrupt resumption
• Prompt engineering with discipline
• Token cost optimisation
• Production LLM observability
• Testing discipline — pytest (including pytest-asyncio)
• Pydantic v2 fluency, type-hinted code throughout

Nice-to-haves

• RAG production experience (vector stores: Pinecone, Qdrant, pgvector)
• Production incident command for LLM-powered systems
• ML engineering background
• Anthropic / Claude API experience in addition to OpenAI
• Data pipeline experience (Airflow, Dagster, Prefect)
• Experience working with cross-team JSI / native bridges (the Python core integrates with a mobile JSI layer)