18 of 18 Model Context Protocol Jobs in the City of London

Claude on Bedrock, Gemini, Azure OpenAI), selected per use case for quality, latency and cost. Interfaces: Tools and Model Context Protocol (MCP) for integration; standards-based APIs and secure auth for client systems. What you'll do Conceptualize fast: embed with stakeholders, frame a business process … serve. Engineer the agent core: apply prompt engineering, context engineering, prompt caching, RAG/context-graph retrieval, memory, tool/function calling, MCP integration and multi-agent orchestration. Integrate to standards: connect agents into client ecosystems through proven integration patterns, standards-based APIs and secure authentication. Make reusability ...

complex software engineering workflows. Tasks may involve debugging, feature implementation, code refactoring, performance optimization, and working with Model Context Protocol (MCP) tools. No prior AI experience is required — your technical expertise is what matters. Responsibilities Design and develop Reinforcement Learning environments that evaluate AI models on realistic … Develop reproducible environments with deterministic verification and golden reference solutions . Design workflows that require AI agents to discover and reason over information using MCP tools and real MCP servers . Evaluate AI-generated software solutions for correctness, maintainability, performance, and scalability . Apply strong knowledge of algorithms, data structures ...

services and interfaces that connect AI capabilities to the products customers and colleagues use every day. You'll play a key role in building MCP integrations, agent-to-agent connectivity and robust API services, while also developing responsive, accessible interfaces in React and TypeScript. What you'll be doing … application and integration layer of AI products end to end, covering APIs, integrations, service boundaries and frontend development. Design, build and maintain MCP servers that safely expose systems, content and tooling to AI agents. Develop agent-to-agent connectivity, including message contracts, state management, retries and failure handling. Design clear ...

language for enterprise microservice integration. Hands-on experience with vector databases and semantic search pipeline design. Experience with Model Context Protocol (MCP). Experience with large-scale data platforms such as Databricks, and search engines such as Elasticsearch, in an analytical or AI feature engineering context. Demonstrated ...

detective security controls (e.g., AWS Config, Security Hub, policy as code, automated compliance scanning). Develop and maintain Model Context Protocol (MCP) servers and reusable agent skills, contributing to an enterprise Agent Skills Marketplace with appropriate guardrails. Design, build, and support AWS services including VPC networking, compute … engineering AWS platforms in enterprise or regulated environments. Familiarity with agentic AI development patterns and tools; experience with AWS Bedrock/Agent-Core and MCP is desirable. Experience with policy as code tools (e.g., OPA, Cedar, Sentinel) and testing/validating policies is desirable. Experience building developer platforms/paved ...

learning and development. Nice to Have: Familiarity with Docker, containers, or infrastructure-as-code. Awareness of the Model Context Protocol (MCP) and modern AI application architectures. Apprenticeship & Support: The role is aligned with the apprenticeship standard. You will receive a full induction, structured training plan, regular ...

solutions, including tool use, workflow orchestration, routing, memory, and multi‐agent patterns Expertise in prompt engineering, structured outputs, and reliability patterns to optimise model performance Ability to implement evaluation frameworks for quality, grounding, task success, safety, latency, and cost Experience deploying AI solutions into production with focus on cost … evaluating multi‐agent AI solutions, agent orchestration patterns, RAG architectures, and enterprise integrations Knowledge of agent communication protocols and interoperability patterns, such as MCP and A2A Ability to balance innovation with practical delivery considerations, including risk, cost, security, and production readiness Confidence contributing to pre‐sales while also being able ...

working with either threat modeling, risk assessing or auditing cloud technologies (AWS, Google and Azure), Generative AI/agentic systems and tool integrations (A2A, MCP) Recognized cloud security certification (CCSP, CCSK, AWS certifications etc.) Solid understanding of internal control concepts with the ability to evaluate and determine the adequacy ...

Senior Software Engineer to own the application and integration layer for a new generation of AI-powered products. The role spans backend, API design, MCP integration and frontend development with React and TypeScript. You will design scalable REST/GraphQL APIs, implement agent-to-agent connectivity, and build production-grade ...

tool, built while the value case is made Delivering client POCs and MVPs: RAG pipelines, agent architectures, LLM integrations and protocol-driven tooling (MCP, tool orchestration) Iterating in short loops: demoing every few days, taking feedback, changing course without ceremony Engineering for production from day one: guardrails, security … data engineering to build the whole thing yourself Hands-on production LLM and agent experience: prompt engineering, agent workflows, RAG, tool orchestration and MCP, with evidence you've shipped AI users actually rely on, and how you proved it could be trusted Evaluation-driven habits: golden datasets, eval frameworks, guardrails ...

batch patterns, data graph design, and activation strategies within D360.Map and integrate external agents from hyperscalers (e.g., Copilot, Gemini) into Agentforce via open standards (MCP, A2A); advise customers on how these systems collaborate within their enterprise architecture.Navigate ambiguous, high-stakes technical conversations with authority — knowing when to prescribe, when … engineering, agent lifecycle management, and hands-on prototype development.Hands-on proficiency in programming (e.g., Python, JavaScript, SQL) and data frameworks.Understanding of agent interoperability standards (MCP, A2A) and the broader external agent ecosystem.Experience operating in complex, matrixed enterprise environments across multiple EMEA markets.Exceptional communicator and storyteller — able to translate architectural complexity ...

tool, built while the value case is made * Delivering client POCs and MVPs: RAG pipelines, agent architectures, LLM integrations and protocol-driven tooling (MCP, tool orchestration) * Iterating in short loops: demoing every few days, taking feedback, changing course without ceremony * Engineering for production from day one: guardrails, security … data engineering to build the whole thing yourself * Hands-on production LLM and agent experience: prompt engineering, agent workflows, RAG, tool orchestration and MCP - with evidence you've shipped AI users actually rely on, and how you proved it could be trusted * Evaluation-driven habits: golden datasets, eval frameworks, guardrails ...

licensing scope, enforced at the point of use, including for AI agents. Build agent-facing data access: retrieval (RAG), vector search, and APIs/MCP servers, with permissions applied before context reaches the model. Apply LLMs pragmatically to data work (metadata generation, classification, entity resolution) with humans ...

ideal candidate will have experience integrating with LLM APIs and building agentic or tool-calling pipelines to implement multi-step reasoning workflows (e.g. MCP, LangGraph). You’ll use your knowledge from a master’s degree (or equivalent experience), utilising a range of methodologies to tackle problems … cyber resilience and legacy software hardening against known vulnerabilities. Develop virtualisation based digital twin environments and implement techniques for assuring operational continuity in the context of CNI. Develop CNl-relevant scenarios with clear threat models, operational continuity criteria, and defensible assumptions; document limitations and known failure modes explicitly. ...

client experience through faster reporting and richer performance insights without increasing operational overhead. They will also design an automation architecture based on an MCP-first approach that allows tools to be replaced easily, new agents to be introduced rapidly, and the platform to evolve with changing technology. The CPO will … infrastructure into the network's primary activation capability. They will develop a unified activation layer that provides a consistent data model and buying interface across paid social and programmatic environments while managing strategic technical partnerships, API integrations, certifications, and evolving industry standards. Navigator's first-party data represents ...

that need: ASKB has become a primary conversational interface, grounded in accuracy, transparency and trusted content, and as firms adopt AI across ASKB, agents, MCP-based tools and connectors, the controls and policies governing content access must extend across the entire Terminal experience. Bloomberg is committed to using client content … this layer end-to-end — from the enterprise admin console through the platform primitives that other product teams, including AI, MCP and connector teams, build on. This is a durable and expanding mandate: as the Terminal and its AI surface grow, you'll ensure the controls, compliance capabilities and policies ...

intelligence, and this role owns the platform foundations that make it possible. You will define the AI-ready data strategy, semantics layer, and MCP-first distribution approach that powers internal product teams, partner integrations, and AI-native customer experiences. This is a highly influential individual contributor role where you will … help establish how ICIS delivers trusted market intelligence through AI. Responsibilities Own the platform mission and roadmap for AI-ready data, semantics, and MCP-first distribution Define the standards, data contracts, schemas, versioning, deprecation approaches, and quality measures that underpin AI-ready data across ICIS Evaluate customer signals and identify ...

excited by the opportunity to define a new product development model and work directly with customers to solve high-value problems? Do you thrive in fast-moving environments where discovery, experimentation, and measurable customer impact are at the heart of every decision? About the Business At ICIS, our mission … delivery. You can engage credibly with engineering and data science teams, understand modern AI production patterns such as RAG, evals, agents, tool use, and MCP, and have recent experience building or prototyping AI-driven solutions. Comfort working in ambiguity. You create structure where none exists, make decisions with incomplete information ...