LLM Engineer — RAG & Retrieval Systems

Pinecone is hiring an LLM Engineer to build and optimise RAG (Retrieval-Augmented Generation) pipelines for our enterprise customers. You will design reference architectures, create developer tooling, and help customers get the most out of semantic search and LLM retrieval.

Responsibilities

• Design and implement production RAG pipelines using Pinecone + LLMs
• Build developer documentation, tutorials, and reference applications
• Work with enterprise customers to optimise retrieval quality and latency
• Contribute to open-source RAG tooling and integrations
• Evaluate embedding models and chunking strategies for specific use cases

Requirements

• Strong Python skills and experience with LangChain, LlamaIndex, or similar
• Deep understanding of vector databases, embeddings, and nearest-neighbour search
• Experience with OpenAI, Anthropic, or Cohere APIs
• Ability to write clear technical documentation