3 of 3 Contract Model Context Protocol Jobs in the UK excluding London

Agentic AI Engineer (.NET) - Contract

Hiring Organisation
Sanderson Recruitment
Location
Bristol, Avon, South West, United Kingdom
Employment Type
Contract
Contract Rate
Up to £500 per day
approval gates so developers can verify and correct agent output before it is merged. Integrate tools and data sources into the agents via MCP (Model Context Protocol). Set up evaluation, guardrails and tests to catch incorrect output early. Work alongside engineering team's and upskill them ...

AI Architecture / Principal AI Engineer

Hiring Organisation
Deloitte
Location
London, South East, England, United Kingdom
Employment Type
Contractor
Contract Rate
Competitive salary
gateway/Bedrock patterns, data residency, SSO/OIDC federation, and cost controls. Experience with Claude/Anthropic, OpenAI, Microsoft Copilot families, including MCP, connectors, skills, and trade-offs. Strong understanding of AI testing disciplines (accuracy, hallucination, bias, prompt evaluations) and AI governance/risk (DPIA, data classification, FCA considerations ...

Senior AI Software Engineer (GenAI)

Hiring Organisation
Infosec
Location
Cardiff, South Glamorgan, Wales, United Kingdom
Employment Type
Contract
Contract Rate
£500 - £700 per day + + Fully remote
behind them. Essential Experience Building and deploying production LLM applications Strong experience with RAG including: Document ingestion Chunking strategies Embeddings Vector search and retrieval Context engineering Prompt orchestration LLM deployment experience, not just experimentation Azure OpenAI, Ollama and/or Vertex AI Python, FastAPI and REST API development LangChain … evaluate and improve model performance How to expose AI capabilities through APIs and enterprise applications Desirable Azure AI Foundry Agentic AI MCP Private LLM deployments Enterprise security and regulated environments Not Suitable If Experience is primarily notebooks, research or experimentation No production LLM deployment experience No RAG implementation experience ...