Job Description
📋 Description Architect and lead multi-agent LLM systems with LangGraph/LangChain/Promptfoo. Build RAG pipelines with hybrid vector search (dense+keyword) using LanceDB/Pinecone. Define workflows for summarization, routing, retrieval, and response with low latency. Develop RAG evaluation frameworks: precision/recall, latency, and hallucination checks. Integrate GPT-4o, PaLM 2, LLaMA, Mistral for task-specific Q&A. Plan agent orchestration and robust fallback in production. 🎯 Requirements 5+ years as an AI/ML Engineer LLMs & GenAI: GPT-4o, PaLM 2, LangGraph, LangChain, Promptfoo RAG Frameworks: LanceDB, Pinecone, ElasticSearch, FAISS Agentic AI: LangGraph multi-agent orchestration and routing Fine-Tuning: BERT/domain transformers tuning, evaluation Infra & MLOps: FastAPI, Docker, Kubernetes (EKS/AKS), Redis Streams
