1 of 1 Permanent Pinecone Jobs in Colchester

production as APIs or services, with attention to latency, cost, scalability, and reliability Design and implement RAG (Retrieval‐Augmented Generation) systems using vector databases (Pinecone, Weaviate, Chroma), including embedding, chunking, and retrieval‐quality evaluation Integrate LLM APIs (OpenAI, Anthropic, etc.) into production services and product workflows Design and build agentic … OpenAI, Anthropic; LangChain or LlamaIndex Agentic AI – LangGraph, LangChain Agents, AutoGen, or CrewAI; tool/function calling, orchestration, memory, and guardrails RAG & vector databases —-Pinecone, Weaviate, or Chroma Databases – PostgreSQL, MongoDB, or Firebase Cloud & deployment – AWS, GCP, or Azure; Docker; CI/CD Security & compliance – secure coding, secrets management, access ...