About the role

You'll build AI-powered features and LLM applications in Python — integrating model APIs, building RAG pipelines and exposing them via APIs — mentored by senior AI engineers.

Responsibilities

- Build and integrate LLM-based features in Python (model APIs, prompts)

- Implement RAG pipelines and work with vector databases

- Expose AI features through REST APIs (FastAPI)

- Process and prepare data with Pandas/NumPy

- Evaluate, test and iterate on prompt/model quality

- Use Git flow and CI/CD

Must-have

- Strong Python fundamentals

- REST API basics and FastAPI (or Flask)

- Hands-on with LLM APIs (OpenAI / Anthropic / similar) and prompting

- Basic ML/data concepts; Pandas / NumPy

- Git basics

- English B2+

Nice-to-have

- RAG, vector databases (pgvector / Pinecone / Chroma), LangChain

- PyTorch / scikit-learn, Hugging Face

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