14 of 14 Part-Time Model Context Protocol Jobs in the UK

collaborative culture through communities of practice and emerging-technology events. You will explore and operationalize emerging patterns such as agent-to-agent communication, model context protocols, and agentic orchestration, turning early-stage concepts into scalable, production-ready capabilities. \n Job Responsibilities \n \n Design, develop, and troubleshoot software … querying languages \n Experience with containerization \n Knowledge of agent-to-agent (A2A) communication concepts \n Familiarity with Model Context Protocol (MCP) \n Experience with agentic orchestrators, personal AI assistants, or AI skills development \n\n ABOUT US \n J.P. Morgan is a global leader in financial ...

stability. You will help deliver GenAI services using public cloud capabilities. You will explore and operationalize emerging patterns such as agent-to-agent communication, model context protocols, and agentic orchestration, turning early-stage concepts into scalable, production-ready capabilities. You will contribute as a team player who seeks … environment using modern programming and database querying languages, including containerization \n Knowledge of agent-to-agent (A2A) communication, Model Context Protocol (MCP), AI skills development, personal AI assistants, or agentic orchestrators \n\n ABOUT US \n JPMorganChase, one of the oldest financial institutions, offers innovative financial solutions ...

deployment of GenAI applications (including Retrieval-Augmented Generation (RAG) pipelines) and agents with planning, memory, and workflow orchestration \n Implement tools and frameworks for model versioning, experiment tracking, and lifecycle management \n Develop systems to monitor model performance and address data and model drift \n Recommend best … Familiarity with advanced AI/ML concepts and protocols, including Retrieval-Augmented Generation (RAG), agentic system architectures, and Model Context Protocol (MCP) \n Hands-on experience with agentic frameworks (LangChain, CrewAI, AutoGen, LangGraph, ADK). \n Strong communication skills for both technical and non-technical audiences. ...

service solutions for documentation, SDKs, configurations, and pipelines to enable rapid deployment of GenAI applications and agents \n \n Implement tools and frameworks for model versioning, experiment tracking, and lifecycle management \n Develop systems to monitor model performance and address data and model drift \n Recommend best … Familiarity with advanced AI/ML concepts and protocols, including Retrieval-Augmented Generation (RAG), agentic system architectures, and Model Context Protocol (MCP) \n \n Exposure to vector stores such as Pinecone, GCP RAG engine, and AWS S3 Vector Buckets \n \n Previous experience deploying and managing ...

accelerate AI solution development. \n Design and develop multi-agent systems for orchestration, agent-to-agent communication, eval, memory, telemetry, and guardrails. \n Apply context and prompt engineering techniques to improve prompt-based model performance. \n Develop and maintain tools and frameworks for prompt-based agent evaluation, monitoring … engineers, data scientists, and ML practitioners. \n Experience in customising and optimizing Github Copilot using VSCode Extension or Model Context Protocol (MCP) \n Experience with AWS and infrastructure-as-code tools such as Terraform. \n Experience in multi-agent orchestration. \n Familiarity with MLOps practices, including ...

differentiator \n \n Python and/or Java for backend service development \n \n LLM integration experience - OpenAI, Anthropic, or equivalent APIs \n \n MCP, REST APIs, Microservices Architecture \n \n Cloud platforms - AWS, Azure, or GCP \n \n \n Preferred\n \n \n Agentic framework experience - LangChain, LangGraph, AutoGen ...

compilation etc. \n\n \n \n Experience with different AI coding tools e.g. Cursor, VSCode agents, Claude code, Codex etc. \n\n \n \n MCP:\n \n \n Experience developing servers and clients \n \n Experience consuming existing servers and clients e.g. Claude desktop, cursor, etc. \n \n AI feedback ...

review AI-generated code with confidence. \n \n Hands-on experience building agentic systems using frameworks such as LangGraph, Microsoft Agentic Framework, or MCP, with a solid understanding of LLM capabilities and risks. \n \n Experience designing and running experiments to validate ideas quickly, using technical prototypes, customer feedback ...

building and shipping LLM/GenAI apps, agentic workflows, multi-agent patterns, tool/function calling, RAG, search, vector databases and integration patterns (e.g., MCP/tool calling). \n Ability to solve complex problems and work effectively with technical and non-technical stakeholders \n Display an “AI-native mindset ...

tuning or DAST onboarding). \n\n \n \n Build working relationships with a small set of partner teams and establish a predictable engagement model (intake path, review checklist). \n\n \n \n Start contributing to security reviews for new features or higher-risk changes—initially ...

Agentic AI & LLM Engineering: \n \n Design and build production-grade agentic systems using major LLM SDKs and agent frameworks; deep knowledge of RAG, MCP servers and prompt engineering at scale. \n\n \n Strong opinions on secure, resilient enterprise deployment of LLM-powered systems; current knowledge of the latest … model capabilities and AI product stacks. \n\n Machine Learning Engineering: \n \n End-to-end ML lifecycle expertise: feature engineering, model training, evaluation and production deployment, including MLOps, monitoring and drift detection. \n\n \n Practical knowledge of ML frameworks (e.g. scikit-learn, PyTorch, XGBoost) and cloud ...

pipelines and semantic search using vector databases such as Pinecone and Chroma, including indexing, retrieval policies, and evaluation. \n Build and integrate agent tools (MCP) and APIs to connect agents with external services, databases, and internal systems, ensuring robust output parsing, error handling, and retries. \n Design and implement robust … evaluation frameworks to systematically assess and measure the performance of AI agents across key operational metrics. \n Practice advanced prompt and context engineering (e.g., Chain-of-Thought, ReAct, function calling/tool-use prompts), implement output validation and guardrails to reduce hallucinations. \n Deploy scalable AI services to cloud ...

practices in AI engineering. \n Use best practices (e.g., MLOps, AIOps) to improve products/services and processes related to AI. \n Optimise existing model serving and data pipelines to meet changing performance and security requirements. \n Hold requirements gathering sessions with business stakeholders and data science teams. … powered development tools like GitHub Copilot or similar platforms (e.g., Kiro, Cursor) to enhance productivity and code generation. \n Knowledge of or experience with MCP to integrate LLMs with external data sources and tools \n\n At JET, this is on the menu: \n Our teams forge connections internally ...

sensitive information across network, cloud, endpoint, and AI-integrated environments. \n \n Extend data classification and DLP coverage to AI ensuring training datasets, model inputs and outputs, and inference logs containing sensitive data are subject to the same controls as the broader data estate. \n \n Lead the engineering … security risks — including training data exposure, model inversion, prompt injection, and the data privacy implications of generative AI and agentic workflows such as MCP-integrated platforms. \n \n Collaborative by default, with a track record of partnering with IT, software engineering, and privacy teams to deliver data security outcomes ...