AI Python Developer / Lead
New
A
apreelHealth-tech AI
Locations: Warszawa, Centrum, Warszawa, Country code: PLContractPrincipal
Salary160 - 180 PLN per hour
Apply NowOpens the employer's application page
Job Details
- Languages
- Pl C2, en C1
- Experience
- 7+ years Python in production at senior+ level
- Required Skills
- PythonMongoDBFastAPIPostgresRedisLangChain
Requirements
- Have 7+ years of Python experience in production at senior+ level.
- Bring deep LangGraph experience, including state graphs, checkpoints, interrupts, multi-agent supervision, and subgraphs.
- Have strong LangChain ecosystem knowledge, including chains, tools, memory, output parsers, and callbacks.
- Have production FastAPI experience with streaming responses, dependency injection, middleware, and async patterns.
- Have production Celery and Redis broker experience, including task ordering, retries, idempotency, priority queues, and dead-letter handling.
- Understand Python concurrency, including asyncio, threading boundaries, and safely mixing synchronous and asynchronous code.
- Have multi-datastore experience with MongoDB, Redis, and Postgres in a single service.
- Have experience using the OpenAI API at scale, including rate limits, retries, fallback model routing, streaming, and tool or function calling.
- Know agent design patterns such as ReAct, plan-and-execute, supervisor patterns, tool-use loops, and interrupt resumption.
- Apply disciplined prompt engineering, evaluation, A/B testing, prompt version control, and regression detection.
- Have experience with token cost optimisation and production LLM observability.
- Use pytest, including pytest-asyncio, and testing approaches such as property-based, snapshot, and eval-based tests.
- Be fluent in Pydantic v2 and type-hinted Python.
Responsibilities
- Audit atlas-ai agent flows, LangGraph state machines, Celery topology, datastore usage, and OpenAI integration patterns.
- Write an operational risk assessment covering failure modes, race conditions, retry semantics, idempotency, and checkpoint integrity.
- Quantify token costs per agent flow and user session.
- Identify high-risk subsystems and propose stabilisation plans.
- Build or harden an evaluation harness with golden cases, regression suites, and hallucination and safety tests.
- Lead knowledge-transfer sessions with the client's AI team.
- Set technical direction for the AI core and lead design of new agent flows and major changes.
- Own production health of the AI surface with platform and SRE support.
- Hire and mentor the AI squad.
- Represent the AI core in cross-team architecture conversations with the client.
View Full Description & ApplyYou'll be redirected to the employer's site
