Experience: 4?8 years
Domain: Large Language Models (LLM), Retrieval-Augmented Generation (RAG), Automation
We are seeking an experienced LLM Engineer to design, develop, and deploy AI-powered solutions using Retrieval-Augmented Generation (RAG) pipelines, FastAPI, and LangChain within the healthcare domain. You will play a key role in implementing scalable backend services, document chunking, context injection, vector search, and real-time automation workflows using LLMs hosted on vLLM or MCP servers.
Tech Stack:
- Languages: Python (FastAPI), SQL
- LLM Orchestration: LangChain, custom RAG modules
- LLM Hosting: vLLM, MCP servers (Model Context Protocol)
- Document Processing: Custom chunking, PDF/Word parsers
- Vector Stores: FAISS, OpenSearch, Qdrant, Chroma
- Databases: PostgreSQL / MySQL
- Cloud: AWS (ECS, S3, Lambda optional)
- Containerization: Docker
- Task Queues: Celery (optional)
- Nice to have: Databricks for data enrichment & batch document analytics