Generative AI / LLM Engineer

The Role: Hands-on development of robust model pipelines, RAG (Retrieval-Augmented Generation) architectures, prompt tuning, and multi-agent integrations.

Experience Range : 4 to 8 years

Location : PAN INDIA

Key Skills We're Looking For

• Proficiency with the Gemini API / SDK (Python/Node.js)
• Frameworks like LangChain or LlamaIndex
• Production experience with Vector Databases (Vertex Vector Search, Pinecone, Pgvector)
• Deep understanding of RAG design patterns and LLM evaluation techniques