5 of 5 Pinecone Jobs in East London

RAG) for augmenting LLMs with domain-specific knowledge. Prompt engineering and fine-tuning for tailoring model behavior to business-specific contexts. Use of embedding stores and vector databases (e.g., Pinecone, Redis, Azure AI Search) to support semantic search and recommendation systems. Building intelligent features like AI-powered chatbots , assistants , and question-answering systems using LLMs and conversational agents. Awareness of More ❯

day. What You’ll Own Architect and develop backend microservices (Python/FastAPI) that power our RAG pipelines and analytics Build scalable infrastructure for retrieval and vector search (PGVector, Pinecone, Weaviate) Design evaluation frameworks to improve search accuracy and reduce hallucinations Deploy and manage services on GCP (Vertex AI, Cloud Run, BigQuery) using Terraform and CI/CD best practices … teams to iterate fast and deliver impact Embed security, GDPR compliance, and testing best practices into the core of our stack Tech Stack Python • FastAPI • PostgreSQL + PGVector • Redis • Pinecone/Weaviate • Vertex AI • Cloud Run • Docker • Terraform • GitHub Actions • LangChain/LlamaIndex What We’re Looking For 5+ years building production-grade backend systems (preferably in Python) Strong background More ❯

production Hands-on experience with frameworks like LangChain, LangGraph, or custom-built agent orchestration setups Familiarity with LLM APIs (OpenAI, Anthropic, Mistral, etc.), embedding stores, retrieval pipelines (e.g. Weaviate, Pinecone), and eval tooling Comfort building and testing AI workflows that interact with external APIs, file systems, simulations, and toolchains Bonus: interest or experience in robotics, mechanical/aerospace workflows, or More ❯

up. What You’ll Do Build scalable backend microservices in Python (FastAPI) to support RAG workflows and user queries Develop and optimise vector search pipelines using tools like PGVector, Pinecone, or Weaviate Design embedding orchestration and hybrid retrieval mechanisms Implement evaluation frameworks (BLEU, ROUGE, hallucination checks) to monitor answer quality Deploy production systems on GCP (Cloud Run, Vertex AI, BigQuery More ❯

varied use cases. Build agentic workflows and reasoning pipelines using frameworks such as LangChain, LangGraph, CrewAI, Autogen, and LangFlow. Implement retrieval-augmented generation (RAG) pipelines using vector databases like Pinecone, FAISS, Chroma, or PostgreSQL. Fine-tune prompts to optimise performance, reliability, and alignment. Design and implement memory modules for short-term and long-term agent behaviours. Deploy models and orchestrate More ❯