About the role

You'll design and own production AI/LLM systems in Python — architecting RAG pipelines and model integrations and mentoring engineers.

Responsibilities

- Architect and build production LLM applications and RAG pipelines

- Design AI feature integrations and expose them via APIs (FastAPI)

- Own evaluation, quality, cost and latency of AI systems

- Work with vector databases and data pipelines

- Lead technical decisions and mentor mid/junior engineers

- Own CI/CD and deployment of AI services

Must-have

- Expert Python

- Production experience with LLM APIs, prompting and RAG

- FastAPI + REST API design; vector databases

- ML fundamentals; Pandas/NumPy

- Cloud (AWS/Azure/GCP), Docker, CI/CD

- System design for AI features

- 5+ years experience (incl. AI/ML in production); English B2+

Nice-to-have

- LangChain/LlamaIndex, fine-tuning, eval frameworks

- PyTorch/scikit-learn, MLOps (MLflow)

- Databricks/Spark, data engineering