• You will help create prompt workflows, retrieval-augmented generation (RAG) pipelines, and AI features that deliver business value safely and reliably
• Build GenAI prototypes and production features using LLM APIs and open-source models
• Develop prompt strategies and evaluate outputs for quality and consistency
• Implement RAG using vector databases and document pipelines
• Create automated tests and evaluation approaches for GenAI responses

Work on responsible AI practices (privacy, safety, bias mitigation)

• Strong Python skills and comfort with APIs
• Understanding of NLP fundamentals and basic ML concepts
• Ability to write clean code and iterate quickly
• Familiarity with LangChain or LlamaIndex (or similar orchestration tools)
• Experience with vector databases (Pinecone, Weaviate, FAISS, Chroma)
• Basic knowledge of embeddings, token limits, context windows, and prompt injection risks

Cloud and Docker exposure