About the role
You will turn business workflows into intelligent automation: from prompt design and retrieval-augmented generation to evaluating and monitoring models in production.
What you'll do
- Build LLM-based features such as chatbots, document understanding and agents.
- Design retrieval pipelines with vector databases and embeddings.
- Evaluate model quality, cost and latency, and iterate quickly.
- Package models and services for reliable production deployment.
What we're looking for
- 3+ years of experience with Python and modern ML tooling.
- Hands-on experience with LLM APIs and frameworks like LangChain or LlamaIndex.
- Understanding of embeddings, vector search and prompt engineering.
- Ability to explain technical trade-offs to non-technical stakeholders.
Nice to have
- MLOps experience
- Fine-tuning open-source models
- Cloud certifications