76 to 100 of 111 Model Context Protocol Jobs in London

flag use cases with broader applicability to the wider AI organization. Champion responsible AI usage, ensuring deployments adhere to firm policies on data security, model governance, and compliance. European Hours Production Support — Lane Assist/POET Provide first‐line support for Lane Assist and the Portfolio Optimization Engine Technology … audiences. Experience gathering and synthesizing requirements across multiple stakeholder groups and influencing product or platform roadmaps. Familiarity with LLM ecosystems (e.g., prompting, RAG, agents, MCP, fine‐tuning, evaluation) and major AI platforms/APIs. Experience in financial services, asset management, or portfolio analytics is a strong plus. Good‐to‐have ...

controls in place so AI outputs remain reliable and cost‐effective. Scale practical AI adoption Design and implement AI workflows as skills, models and MCP tools in OpenWebUI, with cost control, provider routing and observability built in. Partner with other departments to turn AI capabilities into everyday workflows, reusable tools … build durable institutional capability. Reliability, cost control, observability, instruction‐following, usability and adoption matter most. The team designs reusable workflows, skills, models and MCP tools that support Penta’s move towards an AI‐native advisory operating system. Keeping Penta at the forefront of practical AI in PR, communications and strategic ...

convert member and stakeholder feedback into roadmap decisions, product refinements and delivery choices to maximize adoption. Help define practical connectivity and delivery models, including MCP servers and packaged AI Skills, so members can consume ISDA AI capabilities safely within their own environments. Contribute to broader ISDA AI strategy development, including … building production systems directly. Deep understanding of LLMs, retrieval‐augmented generation (including hybrid retrieval across semantic, graph and keyword search, with reranking and embedding‐model selection), knowledge bases, knowledge graphs and ontologies, agentic workflows and skills, evaluation methods (eval harnesses, LLM‐as‐judge, groundedness and faithfulness metrics, tracing ...

tools (e.g. Databricks, NoSQL stores) and AI/ML frameworks (e.g. NLP). LLM integration patterns, RAG pipelines, and agentic AI architectures, including MCP server. Domain experience in Credit Risk, Market Risk, Liquidity or Capital. Experience in defining data strategy for advanced analytical initiatives, including data governance, sourcing, and ethical … skills that can drive your career. By joining Citi, you will not only be part of a business casual workplace with a hybrid working model (up to 2 days working at home per week), but also receive a competitive base salary (which is annually reviewed), and enjoy a whole ...

strangler fig) to deliver clean, modern APIs Ship improvements in fast cycles with measurable gains in performance and reliability Build AI-powered tooling, including MCP servers and AI-assisted CI/CD pipelines Demonstrate how AI transforms developer productivity and code quality What We’re Looking For 6+ years’ backend … experience (Java) Proven experience modernising production systems at scale Hands-on use of AI development tools (e.g. Claude Code, GitHub Copilot, LLMs) Experience with MCP, AI automation, or agentic AI systems Strong understanding of microservices and API design Strong TDD experience Java/Microservices/API design/LLMs/ ...

subject matter specialists—across areas such as agentic application design, AI security and trust, AI operations and observability, data and knowledge engineering, and model platforms and inference—providing the architectural vision, technical governance, and cross-domain coherence that bind their contributions into a unified, enterprise-ready system. You will …/IAP binding, and defense‐in‐depth enforcement Define the layered guardrail framework applied at every boundary, balancing protection with performance Govern the MCP control plane—registry, gateway, and risk scoring—across all internal and third‐party servers Mandate adopt‐over‐build for productized evaluation and observability stacks Establish FinOps ...

quality code and can turn AI capability into real business impact. Key Responsibilities Responsibilities Design, build and maintain core AI platform components - LLM gateway, MCP connector layer, observability tooling, and privacy Proxy Develop and harden MCP connectors across data sources (M365, Salesforce, Moody's, internal systems) through PoC, pilot … building with LLM APIs (Anthropic, OpenAI or similar) in production environments Experience building AI Solutions is essential Experience with agentic frameworks, tool use, and MCP or equivalent connector patterns desirable Familiarity with observability and evaluation tooling for AI systems Understanding of data platforms - Databricks or similar - and how to expose ...

hierarchical delegation). Experience in a post-sales or technical consulting delivery function. Experience enabling technical teams on Agentic AI. Knowledge of Large Language Model (LLM) native metrics (e.g., tokens/sec, cost-per-request) and techniques for optimizing state management and granular tracing. Excellent … communication skills. Responsibilities: Serve as a developer for complex AI applications, transitioning from rapid prototypes to production-grade agentic workflows (e.g., multi-agent systems, MCP servers) that drive measurable Return on Investment (ROI). Architect and code the connective tissue between Google’s AI products and customer's live infrastructure ...

engineering tooling responsibly to improve delivery productivity, including integrated agentic coding assistants, prompt engineering, code review support and, where appropriate, agentic workflow patterns and MCP‐based integrations. Mentor developers and improve team capability across C#/.NET, OpenShift, MongoDB, SQL, messaging, platform engineering and modern engineering practices. Ensure appropriate unit … service delivery capabilities. Knowledge and practical experience of AI‐enabled development tooling, integrated agentic coding assistants and prompt engineering; experience designing agentic workflows or MCP‐enabled integrations is desirable. Risk IT, Product Control IT, ESG IT, regulatory technology or financial‐services domain experience is desirable. #J-18808-Ljbffr ...

more critical architecture domains - such as agentic application design, AI security and trust, AI operations and observability, data and knowledge engineering, or model platforms and inference - serving as the lead authority in your domain across client engagements. You will develop and maintain specialized expertise in the technologies, patterns … decisions for AI platforms (e.g., Arize, LangSmith) and foundational models. Architect model- and tool-agnostic multi-agent systems governed by an MCP Control Plane. Design and implement the Agent Registry as the mandatory system of record and the AI Gateway for runtime policy enforcement. Design and implement a certification ...

Pleo's internal AI infrastructure team, the platform every customer-facing AI feature is built on. The team owns LLM serving (LiteLLM), the MCP gateway and tool registry, agentic runtime, evaluation tooling, and the observability layer that makes AI outputs trustworthy at scale. This is a technical engineering management role … delivery, quality, team development, and ways of working. Own the execution of the platform roadmap including but not limited to LLM gateway, agentic runtime, MCP layer, data retrieval, eval tooling, and the hybrid architecture transition. Manage the stakeholders relationship with Data & AI Products as the primary internal customer and ensure ...

hierarchical delegation). Experience in a post-sales or technical consulting delivery function. Experience enabling technical teams on Agentic AI. Knowledge of Large Language Model (LLM) native metrics (e.g., tokens/sec, cost-per-request) and techniques for optimizing state management and granular tracing. About … yours. Responsibilities Serve as a developer for complex AI applications, transitioning from rapid prototypes to production-grade agentic workflows (e.g., multi-agent systems, MCP servers) that drive measurable Return on Investment (ROI). Architect and code the connective tissue between Google’s AI products and customer's live infrastructure, including ...

traffic environments Build and deploy production AI Agents using raw and fine‐tuned foundational Large Language Models (LLMs), along with sub‐agents, tools, and MCP integrations Architect end‐to‐end ML pipelines, integrating data processing (e.g., Spark, Airflow) with model training, evaluation, and deployment workflows Drive experimentation frameworks, including …/B testing and offline evaluation, to continuously improve model performance and product outcomes Partner cross‐functionally with Product, Engineering, and Data leadership to translate business challenges into impactful ML solutions, collaborating with purpose and influencing at senior levels Mentor and elevate senior individual contributors, fostering a culture ...

Execution: Ensure on-time delivery of AI solutions that meet government-grade security, privacy, accessibility, and performance standards Coordinate technical work across multiple teams: model customisation, security hardening, integration with government systems, bilingual support Establish governance checkpoints appropriate for high-stakes government deployments Problem-solve complex technical challenges … Strong understanding of enterprise software deployment architectures (cloud, on-premises, hybrid, air-gapped) Working knowledge of or experience with modern AI: LLMs, agentic systems, MCP, RAG, fine-tuning, evals, and responsible AI would be a strong differentiator Comfortable discussing API integrations, model inference, data pipelines, and ML operations with ...

safely, with the right permissions, and in ways enterprises can trust. We ship for claude.ai, Claude Code, Cowork, and the API. We own the MCP proxy that routes every tool call and the OAuth and token management that keeps connections authenticated. We’re also core contributors to the MCP spec … t. Key responsibilities Lead a team of engineers building the connectivity infrastructure that powers tool use across the company's product suite, from the MCP proxy to OAuth and token management Take an inclusive, equitable approach to hiring and coaching top technical talent, and maintain a high‐performing team Coach ...

infrastructure to scale impact beyond individual partnerships. Responsibilities Serve as a deep technical partner to mission-driven organizations through advising on evals, agent architectures, context engineering, cost optimization, and more Provide hands-on support … partner engineering teams through pair programming, prototyping, and code contributions that accelerate their development Develop public goods infrastructure that benefits entire ecosystems through benchmarks, MCP’s, and Agent Skills Identify challenges unique to social impact partners, and contribute findings and improvements back to product, engineering, and research Create technical presentations ...

facing engineering role – forward deployed engineering, technical consulting, or engineering advisory Experience with Claude Code enterprise deployment, AI agent integration into development workflows, or MCP server development External presence – writing, speaking, or community contribution in the software engineering or engineering leadership space Experience working alongside or within partner ecosystems such … Anthropic, Databricks, or AWS at a senior level Experience in a Palantir, Anthropic, DeepMind, or similar forward‐deployed engineering model #J-18808-Ljbffr ...

complex patterns (e.g., ReAct, self‐reflection, hierarchical delegation). Experience in a post‐sales or technical consulting delivery function. Knowledge of Large Language Model (LLM) native metrics (e.g., tokens/sec, cost‐per‐request) and techniques for optimizing state management and granular tracing. Ability to travel to regional stakeholders … needed. Responsibilities: Serve as a developer for complex AI applications, transitioning from rapid prototypes to production‐grade agentic workflows (e.g., multi‐agent systems, MCP servers) that drive measurable Return on Investment (ROI). Architect and code the connective tissue between Google’s AI products and customer’s live infrastructure, including ...

takes Nice to Have Former technical founder or CTO – you have built products and teams under commercial pressure and client scrutiny Experience with MCP server development, tool ecosystem integration, and enterprise agent deployment patterns Experience working alongside or within partner ecosystems such as Anthropic, or AWS at a senior level … External presence – writing, speaking, or thought leadership in the AI Engineering space Experience in a Palantir, Anthropic, DeepMind, or similar forward-deployed engineering model #J-18808-Ljbffr ...

complex patterns (e.g., ReAct, self-reflection, hierarchical delegation). Experience in a post-sales or technical consulting delivery function. Knowledge of Large Language Model (LLM) native metrics (e.g., tokens/sec, cost-per-request) and techniques for optimizing state management and granular tracing. Ability to travel to regional stakeholders … yours. Responsibilities Serve as a developer for complex AI applications, transitioning from rapid prototypes to production-grade agentic workflows (e.g., multi-agent systems, MCP servers) that drive measurable Return on Investment (ROI). Architect and code the connective tissue between the company’s AI products and customer's live infrastructure ...

complex patterns (e.g., ReAct, self-reflection, hierarchical delegation). Experience in a post-sales or technical consulting delivery function. Knowledge of Large Language Model (LLM) native metrics (e.g., tokens/sec, cost-per-request) and techniques for optimizing state management and granular tracing. About the job As a Forward … yours. Responsibilities Serve as a developer for complex AI applications, transitioning from rapid prototypes to production-grade agentic workflows (e.g., multi-agent systems, MCP servers) that drive measurable Return on Investment (ROI). Architect and code the connective tissue between Google’s AI products and customer's live infrastructure, including ...

J.P. Morgan is seeking an Applied AI ML Lead for the LLM Suite Engineering to design and deliver production-grade AI/ML and agentic solutions that integrate with existing systems. You will own technical ...

existing and emerging product lines, including the Talent CRM and Workforce Suite, and provides data-as-a-service to customers through channels such as MCP/API as an emerging commercial channel. Its core capabilities span the data models, taxonomies and integrations that underpin talent and workforce decisions across … right. Beyond internal embedding and direct commercial sales, the platform is open — customers and partners can build on top of it through MCP and API access. You will work with product leadership to set the strategy, agree what the platform provides internally, decide what becomes customer-facing, and define ...

market is yours.Responsibilities: Serve as a developer for complex AI applications, transitioning from rapid prototypes to production-grade agentic workflows (e.g., multi-agent systems, MCP servers) that drive measurable Return on Investment (ROI). Architect and code the connective tissue between Google’s AI products and customer's live infrastructure … Technical Discovery Sessions* French (Fluent)* German (Fluent)* Multi-agent Systems* LangGraph* CrewAI* ADK* ReAct* Self-reflection* Hierarchical Delegation* Post-sales* Technical Consulting* Large Language Model (LLM) Metrics* State Management Optimization* Granular Tracing* API Integration* Observability Frameworks* Development Best Practices #J-18808-Ljbffr ...

evals, environments, rewards, graders, or training data. Experience helping organizations use AI more effectively, including integrating with third‐party tools via APIs, CLIs, and MCP servers. Strong data engineering skills: pipelines that handle large volumes reliably in production, LLM‐powered enrichment steps, and a focus on improving data quality. Experience … expert review flows (a busy domain expert should be able to validate a task in under five minutes) that hold up when a frontier model learns to game them. Cut the time from 'rough task idea' to 'task in a production training run' from days to hours. ...