7 of 7 Permanent pgvector Jobs in the UK

Well Help You With Them Experience with advanced LLM techniques: agents, tool use, and agentic workflows Experience with vector databases (Pinecone, Weaviate, pgvector) for RAG applications Experience with feature stores (Feast, AWS Feature Store) Experience with containerisation (Docker) and orchestration (Kubernetes, ECS) Familiarity with Infrastructure as Code (Terraform, CloudFormation) Experience ...

Cache Augmented) Architecture: Define architectural patterns for end-to-end RAG pipelines, including chunking, embedding, vector search (e.g., Azure Cognitive Search, pgvector), and reranking. Ensure designs include standards for lineage, observability, and evaluation (e.g., RAGAS). Cross-Cloud & Vendor Integration : Create and maintain decision frameworks for platform selection (e.g., Copilot ...

front-end applications with React, TypeScript, and frameworks like Next.js or Vite. Integrate LLMs (e.g., OpenAI, Anthropic, Mistral) and vector databases (e.g., ChromaDB, Pinecone, PGVector). Deploy solutions using AWS or Azure, Docker, Kubernetes, and Terraform. Implement CI/CD pipelines and monitor LLM performance using tools like Langsmith ...

modern software architecture • Understanding of prompt design and managing AI-generated outputs • Ideally have experience in RAG pipelines and vector databases (e.g. Pinecone, Weaviate, pgvector) • Familiarity with cloud platforms is advantageous (AWS, Azure or GCP) • A proactive mindset with the ability to work effectively in a collaborative team ...

roles Strong Python Experience building and deploying LLM applications (OpenAI, Anthropic, Gemini, etc.) Deep familiarity with RAG methodologies, embeddings, and vector databases (Pinecone, Weaviate, pgvector) Robust API integration experience, including working with third-party datasets, web APIs, or scrapers A product mindset, enjoys crafting scrappy prototypes that evolve into polished ...

very large volumes of time-series data. Hands-on understanding of stream ingestion patterns (MQTT). Experience with graph or Vector databases ( Neo4j, Pinecone, pgvector) and modelling complex, highly relational domains. Familiarity with modern data stack components (e.g., data lakes, streaming, or batch/real-time pipelines). ...

roles Strong Python Experience building and deploying LLM applications (OpenAI, Anthropic, Gemini, etc.) Deep familiarity with RAG methodologies, embeddings, and vector databases (Pinecone, Weaviate, pgvector) Robust API integration experience, including working with third-party datasets, web APIs, or scrapers A product mindset, enjoys crafting scrappy prototypes that evolve into polished ...