AI Engineer

Build and optimize LLM, RAG, and multi-agent workflows for production use cases. Design retrieval systems using vector search, reranking, and metadata filtering. Fine-tune, evaluate, and benchmark models to improve output quality and business impact. Deploy AI/ML services with strong standards for latency, scalability, and observability. Develop data, inference, and experimentation pipelines in partnership with product and engineering teams.

Strong Python and SQL skills with solid machine learning and NLP fundamentals. Experience with LangChain, LangGraph, LlamaIndex, prompt engineering, and retrieval optimization. Familiarity with vector databases and search tools such as Pinecone, OpenSearch, FAISS, or pgvector. Experience with Docker, Kubernetes, MLflow, CI/CD, and cloud platforms such as Azure.