26 to 46 of 46 pgvector Jobs in the UK

/functions callable by AI agents (tool schemas, function calling, structured outputs). Experience with retrieval-augmented generation (RAG) : vector databases (e.g., Pinecone, Weaviate, pgvector), embeddings, and chunking strategies. Working knowledge of prompt engineering and evaluation techniques for agent reliability, safety, and cost control. Familiarity with orchestrating multi-agent workflows ...

like Llama/Mistral) and orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel, or equivalent). Practical experience with RAG, embeddings, and vector databases (Pinecone, Weaviate, pgvector, Azure AI Search). Familiarity with agentic architectures, function/tool calling, and structured outputs. Prompt engineering and evaluation experience, with awareness of guardrails ...

emphasis on Python development in production environments Proven expertise in building and deploying generative AI applications, leveraging LLMs, vector databases like Pinecone, Weaviate, or pgvector, and modern open-source agentic frameworks Practical experience with microservices architecture, RESTful APIs, cloud platforms such as AWS, GCP, or Azure, and containerization with Docker ...

like Llama/Mistral) and orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel, or equivalent). Practical experience with RAG, embeddings, and vector databases (Pinecone, Weaviate, pgvector, Azure AI Search). Familiarity with agentic architectures, function/tool calling, and structured outputs. Prompt engineering and evaluation experience, with awareness of guardrails ...

LangChain, CrewAI, Agentforce or similar Foundation model providers: Claude Code/Codex/Gemini, OpenAI or AWS Bedrock Vector databases: Pinecone, Weaviate, LlamaIndex or pgvector Cloud platforms: AWS Bedrock, GCP Vertex AI or Azure AI Studio CI/CD for AI: version-controlled prompts, automated testing, deployment pipelines ...

etc.) critically and effectively as part of their day-to-day workflow. Bonus points for: Experience with retrieval-augmented generation (RAG) and vector databases (pgvector, Pinecone, or similar). Experience designing multi-agent systems and agent orchestration patterns. Familiarity with LLM observability tools (LangSmith, Langfuse, Arize, or similar). Experience ...

LangChain, CrewAI, Agentforce or similar Foundation model providers: Claude Code/Codex/Gemini, OpenAI or AWS Bedrock Vector databases: Pinecone, Weaviate, LlamaIndex or pgvector Cloud platforms: AWS Bedrock, GCP Vertex AI or Azure AI Studio CI/CD for AI: version-controlled prompts, automated testing, deployment pipelines ...

LangChain, CrewAI, Agentforce or similar Foundation model providers: Claude Code/Codex/Gemini, OpenAI or AWS Bedrock Vector databases: Pinecone, Weaviate, LlamaIndex or pgvector Cloud platforms: AWS Bedrock, GCP Vertex AI or Azure AI Studio CI/CD for AI: version‐controlled prompts, automated testing, deployment pipelines ...

LangChain, CrewAI, Agentforce or similar Foundation model providers: Claude Code/Codex/Gemini, OpenAI or AWS Bedrock Vector databases: Pinecone, Weaviate, LlamaIndex or pgvector Cloud platforms: AWS Bedrock, GCP Vertex AI or Azure AI Studio CI/CD for AI: version-controlled prompts, automated testing, deployment pipelines ...

across teams. Retrieval-Augmented Generation (RAG) & Knowledge Architecture: Expertise architecting RAG and knowledge-grounded systems—chunking strategies, embeddings, vector databases (e.g., Pinecone, Weaviate, Chroma, pgvector, FAISS), hybrid search, reranking, and retrieval evaluation. Familiarity with advanced patterns such as GraphRAG and agentic RAG to maximize factual grounding and minimize hallucination … AutoGen). Experience with cloud AI platforms (e.g., Amazon Bedrock, Azure OpenAI/AI Foundry, Google Vertex AI), vector databases (e.g., Pinecone, Weaviate, Chroma, pgvector, FAISS), containerization and orchestration (Docker, Kubernetes), and distributed computing is advantageous. Architecture Design: Ability to design end-to-end Generative and Agentic AI architectures that ...

Knowledge of DevOps culture and practices; Nice to have: Advanced degree, experience building user-facing GenAI/LLM software applications, vectors and embeddings with pgvector or chromadb, LLM RAG/Agent concepts, Neo4J, GraphQL, CI/CD tools such as GitHub Actions or GitLab CI, AWS Managed Services, FastAPI, NextJS ...

comfort working with AI tools and prompting. An understanding of point in time data is a strong plus Also desirable: experience with vector databases (pgvector, Pinecone, Weaviate, Qdrant or similar); machine learning experience (PyTorch, TensorFlow, XGBoost/LightGBM) for building, maintaining and extending existing models; Bloomberg API integration to Python ...

Llama/Mistral) and orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel, or equivalent). Practical expertise in RAG design, embeddings, and vector databases (Pinecone, Weaviate, pgvector, Azure AI Search). Experience with agentic architectures, function/tool calling, and structured outputs. Solid prompt engineering, evaluation, and LLM guardrail/safety experience. ...

paved road: self-hosted LangSmith and LangGraph Platform as the agent runtime and evaluation plane, model providers behind a swappable gateway seam, PostgreSQL with pgvector plus ClickHouse and S3-compatible object storage as the data platform, Neo4j Enterprise as the semantic knowledge graph, an agent memory plane serving episodic ...

loops: planner/executor/verifier patterns, tool‐use schemas, retry + escalation logic. Build retrieval pipelines: chunking strategy, vector DB choice (Pinecone/pgvector/Weaviate), reranking, freshness handling. Stay current on Anthropic + OpenAI release notes; adjust prompts + schemas when APIs evolve. We treat the foundation‐model ...

term data strategy Helping build and mentor the future data engineering team as the company scales Python, PostgreSQL, MongoDB, vector databases (Qdrant, Milvus or pgvector), Apache Spark, Apache Airflow, Kafka, Elasticsearch/OpenSearch, Pandas, Polars. What they're looking for: 7+ years of experience in data engineering or backend engineering ...

graph models for complex reaction networks, define the semantic ontologies that let AI reason across different chemical data types, and design vector search (e.g. pgvector, Pinecone) for similarity lookups across large molecular sets. Design the telemetry pipeline. Specify streaming ingestion for high-frequency robot and sensor data, with zero loss ...

regression tests, and release criteria to ensure reliability. Integrate AI into production systems Connect models to APIs, data systems, authentication, vector databases (Pinecone, Weaviate, pgvector), and cloud platforms. Operate & monitor AI systems Track quality, safety, hallucinations, drift, latency, and cost; troubleshoot failures and iterate. Cross-functional collaboration Work with product ...

optimisation. A track record of diagnosing and fixing performance bottlenecks in live systems through profiling and measurement. Nice to Have: Experience with PostgreSQL/pgvector, OpenSearch (or Elasticsearch), Spark/Delta Lake, AWS, NoSQL databases, or Rust/C++ is useful. The Founders You'll partner with a founding team ...

without: Postgresql dba, core development/maintenance and performance optimisation (sharding, partitions). Experience with clustering, and extensions such as pgvector PostGIS, and AGE very useful. Additional skills in Oracle or MSSQL would also be required. Candidate should have experience in the Latest version of Oracle Performance optimisation – index tuning ...

Experience managing database clusters and failover Strong data modelling experience Experience working closely with development and infrastructure teams Experience with PostgreSQL extensions such as pgvector, PostGIS or AGE would be beneficial Additional MSSQL experience would be useful Single British Nationality SC clearance as a minimum, with DV targeted Ability ...