Generative AI Engineer - RAG

Job Summary

Design and build production retrieval-augmented generation systems that answer questions from enterprise content accurately and securely.

What you'll do

• Design RAG pipelines: ingestion, parsing, chunking, embeddings and hybrid search
• Implement permission-aware retrieval and metadata filtering
• Build evaluation sets and measure retrieval and answer quality
• Optimise latency and cost; implement caching and model routing
• Deploy and monitor RAG services in the cloud
• Mentor junior engineers

What you'll bring

• 3-6 years of software engineering experience, including at least 1-2 years with LLM applications
• Strong Python and API development skills
• Hands-on experience with vector databases and embeddings
• Experience with at least one of Amazon Bedrock, Azure OpenAI or Vertex AI
• Understanding of evaluation methods for LLM and RAG systems

Nice to have

• Experience with Azure AI Search, OpenSearch or pgvector at scale
• LLMOps and tracing tools (Langfuse, LangSmith)
• Document AI (Textract, Document Intelligence)

Tech stack

• Python
• LangChain / LlamaIndex
• Amazon Bedrock
• Azure OpenAI
• pgvector
• OpenSearch
• Azure AI Search
• FastAPI
• Docker
• Kubernetes

Location

Hyderabad, Telangana, India

Work authorization

Must be eligible to work in India