16 of 16 Model Context Protocol Jobs in Manchester

Apply Prompt Engineering and Context Engineering techniques to optimise AI performance and accuracy. Implement AI solutions using frameworks such as LangChain , LangGraph , and MCP . Integrate AI services and enterprise platforms through REST APIs and cloud-native architectures. Deliver scalable, secure, and reliable solutions using Python … Natural Language Processing (NLP) Prompt Engineering , Context Engineering AI Agents , Agentic AI , Multi-Agent Systems LangChain , LangGraph , Model Context Protocol (MCP) RAG , Embeddings , Vector Databases Python , SQL , REST APIs Git , CI/CD Cloud Platforms (Azure, AWS, or GCP) LLM & AI Agent Testing and Evaluation Desirable ...

engineering role, not a configuration one. As Salesforce grows into a serious AI platform, you'll be building with Agentforce, Einstein, Prompt Builder, Model Builder, and Data Cloud to create agents and AI‐driven features that hold up under real workloads. The work varies a lot. … solutions for large‐scale environments supporting hundreds or thousands of Salesforce users. Nice to have: familiarity with the Model Context Protocol (MCP), vector search and embeddings, or Python for AI tooling. Consulting & Delivery Proven experience translating complex business requirements and user stories into scalable technical solutions. Experience ...

products with clear human oversight, measurable outcomes and safe rollback. Principal Accountabilities Design, build and operate the enterprise agentic platform, including orchestration, runtime services, model routing, memory, identity and policy enforcement. Develop reusable agent frameworks, SDKs and patterns that enable engineering teams to build secure, scalable AI agents consistently. … controls. Integrate agents securely with enterprise platforms, cloud services, APIs and knowledge sources using modern integration standards and Model Context Protocol (MCP). Build production-grade agent services using Python, cloud-native architectures, event-driven design, automation and Infrastructure as Code. Implement robust evaluation, observability and continuous ...

MLOps framework, governance and best practices as per industry standards Designing and delivering end-to-end AI/ML systems, from data preparation and model development to model deployment, feature stores, model management and monitoring model management Delivering solutions using the latest GenAI and Agentic Frameworks … Generative and Agentic AI frameworks such as LangChain, LlamaIndex, CrewAI, Autogen, Google ADK, or similar. Ability to design and implement RAG pipelines, agentic workflows, MCP and integration with LLM APIs (OpenAI, Anthropic, Hugging Face OR similar). Proficiency in CI/CD and containerisation: GitHub Actions, Azure DevOps, Docker, Kubernetes. ...

scale their impact. We value your AI skills if have built fluency across the agentic engineering toolchain — coding harnesses like Claude Code or Cursor, MCP servers, custom skills, or agent frameworks. And you can describe projects where you shipped real work with these tools. You know how to drive ...

RBAC and Cost Controls. Software Engineering: Clean Code (SOLID, DRY), DDD, modular architecture, TDD, code quality tools. AI Engineering (Desirable): RAG pipelines, agentic workflows, MCP, LLM integration (OpenAI, Gemini or other models from Huggingface), LangSmith, TruLens. Agentic Frameworks (Desirable): LangChain, CrewAI, Autogen, OpenAI Agents, Google ADK. WHAT YOU'LL LOVE ...

scale their impact. We value your AI skills if have built fluency across the agentic engineering toolchain — coding harnesses like Claude Code or Cursor, MCP servers, custom skills, or agent frameworks. And you can describe projects where you shipped real work with these tools. You know how to drive ...

scale their impact. We value your AI skills if have built fluency across the agentic engineering toolchain — coding harnesses like Claude Code or Cursor, MCP servers, custom skills, or agent frameworks. And you can describe projects where you shipped real work with these tools. You know how to drive ...

estates to lakehouse or metadata-driven architectures. Customer Data Platforms or event-driven systems. Data-quality tools such as dbt tests or Great Expectations. MCP servers or governed natural-language data interfaces. Financial crime, fraud or regulatory-reporting data. Power BI administration and semantic modelling. The opportunity This ...

estates to lakehouse or metadata-driven architectures. Customer Data Platforms or event-driven systems. Data-quality tools such as dbt tests or Great Expectations. MCP servers or governed natural-language data interfaces. Financial crime, fraud or regulatory-reporting data. Power BI administration and semantic modelling. Why apply? This ...

code and you steered it to production, or you've built fluency across the agentic engineering toolchain — coding harnesses like Claude Code or Cursor, MCP servers, custom skills, or agent frameworks. And you can describe a clear, repeatable workflow: how you prompt, how you scope tasks, how you drive … role? Design, develop, and deploy scalable web applications and services, contributing to web technology and framework stack decisions, use case design, and data model design Drive architecture discussions, take ownership and responsibility over new projects, and deliver high-quality software within tight timelines Partner with security and compliance teams ...

Responsibilities Build production-grade GenAI, LLM, RAG and Agentic AI solutions Develop AI Agents and Multi-Agent Systems Work with LangChain, LangGraph and MCP Build intelligent retrieval using Embeddings, Vector Databases and Semantic Search Apply Prompt & Context Engineering Integrate AI solutions through REST APIs and cloud platforms Test, evaluate … Strong Python and SQL Hands-on experience with LLMs, RAG, AI Agents and Agentic AI Experience with LangChain and/or LangGraph Experience with MCP Knowledge of Embeddings and Vector Databases Experience deploying AI solutions in enterprise environments Cloud experience across Azure, AWS or GCP Understanding of LLM evaluation ...

review steadily upward. Pipeline Engineering Build and maintain the agentic pipeline: agent harness, blueprint engine interleaving deterministic steps (lint, build, git) with AI reasoning, MCP tool layer exposing internal APIs, warm sandbox pool, and retrieval over the codebase, tickets, and historical PRs. Own the economics of the pipeline: observability over … agent-proposed solution meets performance, scalability, and reliability requirements, and challenging designs that will not hold up under real workloads. Experience building agent infrastructure: MCP servers and tool layers, sandboxed execution, and CI/CD adapted for agent-driven workflows. Deep enough .NET/C# and SQL reading fluency ...

agent sessions, and review outcomes critically before they ship. Build and maintain the team’s agentic tooling: custom Claude Code skills and sub-agents, MCP tools exposing internal APIs, prompt/context conventions (CLAUDE.md), and automated review pipelines. Design the verification that makes agent speed safe: test strategy, quality … communication: design docs, specifications, PR descriptions, and commit history that both humans and agents can act on. Bonus points if you have Experience building MCP servers or exposing internal APIs as agent-callable tools. Experience with LLM evaluation: eval suites, behavioural test design, or benchmarking agent workflows. Functional programming ...

workflow, and the moments that earn trust. Work at the frontier of the stack: reason with Engineering about models, context, tools like MCP, and orchestration, and where each one changes the product. Accelerate your own output with AI: use AI tools actively across research, synthesis, prototyping, and analysis, always … grown products people love. Real fluency with how modern AI products work. You are familiar with evals, agentic workflows, context, and tools like MCP, and you have clear judgment about where AI earns its place and where it does not. A systems thinker. You see how the pieces ...

hand - and the newer stuff. Testing AI-powered systems, using AI tooling to supercharge your own output, getting hands-on with Playwright MCP and agentic workflows before most QA engineers have even heard of them. If you're the kind of person who takes genuine pride in the quality … core platforms, and a modern serverless stack in Node.js, TypeScript, SvelteKit and GCP. You'll also get early hands-on time with Playwright MCP and AI agents as we ship real features into production - this is genuinely new territory for most teams. You'll work closely with engineers to catch ...