What you'll do
- Build retrieval-augmented generation (RAG) pipelines and AI agents
- Design evaluation suites that measure quality, cost and latency
- Fine-tune and serve models where off-the-shelf APIs fall short
- Partner with product engineers to ship AI features to production
What we're looking for
- 3+ years building ML or LLM-based systems in production
- Strong Python; familiarity with PyTorch or similar frameworks
- Hands-on experience with embeddings, vector search and prompt design
Nice to have
- MLOps experience (model serving, monitoring)
- Published work or open-source contributions
Skills
- Python
- PyTorch
- LLMs
- RAG
- Vector databases
- MLOps