AI LLM Retrieval Engineer

This role involves architecting and maintaining client-specific and internal RAG pipelines, including embedding generation, document chunking, and metadata tagging. This role requires collaboration with enterprise clients to assess data landscapes, retrieval requirements, and grounding needs. You will select, test, and optimize embedding models (text, multimodal) for accuracy and efficiency, design retrieval strategies (dense, sparse, hybrid) to maximize precision and recall, and establish and monitor evaluation metrics for retrieval performance. The role also includes maintaining documentation for internal and client teams, staying current with advancements in vector databases and retrieval frameworks.