351 to 375 of 586 Model Context Protocol Jobs

capability, including designing, developing and productionising AI-enabled solutions using retrieval-augmented generation, embeddings, vector search, context/prompt engineering, agentic AI patterns, MCP-based extensibility, and Microsoft ecosystem AI tooling. The role ensures these solutions are grounded in reliable, well-governed and secure data foundations. What … solutions for resilience, observability, cost-efficiency and maintainability across production environments. Design and implement custom AI-enabled systems and components, including retrieval-augmented generation, MCP-based extensibility, agentic AI architectures, embeddings, vector-based retrieval and context/prompt engineering. Build and productionise AI solutions using the Microsoft ecosystem, including ...

architecture and delivery of multi-agent AI systems for high-value business use cases. defining engineering standards across orchestration architectures, context engineering, MCP integration, memory design, fine-tuning, evaluation frameworks and multimodal systems. building reusable AI capabilities including agent tools, MCP servers, skills and shared engineering assets. establishing quality … powered systems at enterprise scale. Expert-level Python engineering. Multi-agent architectures and orchestration frameworks. Context engineering, retrieval systems and memory architectures. MCP server and SKILL.md design and enterprise tooling integration. Model fine-tuning at scale (PEFT/(Q)LoRA). Building end-to-end voice AI pipelines ...

practical LLM workflows, agents, skills and tools that support advisory teams, client delivery and internal operations. Implement reusable AI capabilities using OpenWebUI, LiteLLM and MCP tools. Work across prompting, context engineering, structured outputs, evaluation, provider routing and human‐in‐the‐loop workflows. Move useful applications and automations quickly from … 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 ...

management, forecasting and optimisation (including usage‐based pricing shifts), and the staff access model. This includes: AI safety for internal use: sandboxing, policy, integrations, MCP governance, usage guardrails and monitoring expectations. The three platform pillars: control, monitoring and sandboxing (LLM and MCP gateway, anonymisation, local hardening, sandboxed cloud agent hosting … built or significantly scaled a team. Current, hands‐on fluency with the modern AI stack: frontier model platforms, agentic tooling and harnesses, MCP and integration patterns, evals, prompt and context engineering. AI security and governance: sandboxing, gateways (LLM, MCP, AI), DLP, guardrail enforcement and data‐boundary reasoning; able ...

agent approaches, and define evaluation, safety, and monitoring strategies for production use Own production deployment patterns including containerization, continuous integration and delivery, automated testing, model and prompt registries, model and version governance, monitoring and alerting, and rollback strategies Architect and deploy scalable, reliable, and secure machine learning … evaluation and safety patterns Familiarity with agentic building blocks and standards, including orchestration frameworks, context and memory management, and interoperability protocols such as MCP Experience with machine learning frameworks and data science packages such as PyTorch, TensorFlow, scikit‐learn, NumPy, pandas, SciPy, and statsmodels Experience deploying to AWS, including ...

agent approaches, and define evaluation, safety, and monitoring strategies for production use Own production deployment patterns including containerization, continuous integration and delivery, automated testing, model and prompt registries, model and version governance, monitoring and alerting, and rollback strategies Architect and deploy scalable, reliable, and secure machine learning … evaluation and safety patterns Familiarity with agentic building blocks and standards, including orchestration frameworks, context and memory management, and interoperability protocols such as MCP Experience with machine learning frameworks and data science packages such as PyTorch, TensorFlow, scikit-learn, NumPy, pandas, SciPy, and statsmodels Experience deploying to AWS, including ...

secure, observable, reusable and governed by default. You will also contribute to the production foundations needed to operate AI capabilities reliably, including LLMOps, model access patterns, prompt and agent lifecycle practices, observability and secure enterprise integration. What you’ll be doing Designing and building AI platform capabilities on Azure … evaluation practices for agent configurations, prompts and AI workflows, including testing, controlled change and release readiness Designing secure tool-access patterns for agents, including MCP/tool abstraction, credential management and enterprise API integration. Contributing to AgentOps and GenAIOps capabilities, including telemetry, run history, task outcomes, error analysis and feedback ...

management, forecasting and optimisation (including usage-based pricing shifts), and the staff access model. This includes: AI safety for internal use : sandboxing, policy, integrations, MCP governance, usage guardrails and monitoring expectations. The three platform pillars : control, monitoring and sandboxing (LLM and MCP gateway, anonymisation, local hardening, sandboxed cloud agent hosting … built or significantly scaled a team. Current, hands-on fluency with the modern AI stack: frontier model platforms, agentic tooling and harnesses, MCP and integration patterns, evals, prompt and context engineering. AI security and governance: sandboxing, gateways (LLM, MCP, AI), DLP, guardrail enforcement and data-boundary reasoning; able ...

Engineering, Computer Science or equivalent; advanced degree preferred. Agentic AI/LLMs: LLM orchestration, prompt engineering, context‐window management and production guardrails; MCP, tool‐augmented agents and RAG at enterprise scale. Enterprise integration: Integrating AI into enterprise systems via APIs and data pipelines, with strong security, data governance ...

Engineering, Computer Science or equivalent; advanced degree preferred. Agentic AI/LLMs: LLM orchestration, prompt engineering, context-window management and production guardrails; MCP, tool-augmented agents and RAG at enterprise scale. Enterprise integration: Integrating AI into enterprise systems via APIs and data pipelines, with strong security, data governance ...

Engineering, Computer Science or equivalent; advanced degree preferred.* **Agentic AI/LLMs:** LLM orchestration, prompt engineering, context-window management and production guardrails; MCP, tool-augmented agents and RAG at enterprise scale.* **Enterprise integration:** Integrating AI into enterprise systems via APIs and data pipelines, with strong security, data governance ...

Solutions Architect to design end-to-end AI/LLM solutions for enterprise customers, leveraging Tencent Cloud TokenHub, foundation models, AI Agents, and MCP ecosystem. You will lead technical discovery workshops, architecture design sessions, POCs, validation, and production deployment planning, collaborating with customer engineering teams to deliver scalable, reliable ...

Solution Architect to accelerate enterprise AI adoption in Europe. You will design end-to-end AI and LLM solutions leveraging TokenHub and MCP ecosystem, working with enterprise customers and cross-functional teams. Required are 2+ years in Gen AI/LLMs, strong cloud and MLOps experience, and excellent English. Mandarin ...

Demonstrable AI engineering depth. You can show real systems where you made substantive decisions about agent harnesses, evals, hallucination containment, performance, agent sandboxing or MCP/tool design. Strong product engineering and technical judgment. You ship across interface, backend, data and deployment, reason from first principles and choose tools deliberately. ...

Claude (Anthropic) or Copilot Highly desirable (not essential): Python for AI tooling and evaluation scripts Semantic Kernel or LangChain frameworks Linux/Docker MCP experience If you feel this role meets some of the above skillset and open to learning more about AI tools whilst in post, my client offers ...

Will Be Doing Building real product features across Rebel end-to-end, with support and guidance from senior engineers Working with LLMs, agents, and MCP integrations from day one Learning by shipping: we believe the fastest way to grow is to have real ownership Contributing to our open-source ecosystem ...

including the component library, design tokens and documentation Extend the design system for AI-assisted development using Storybook and machine-readable interfaces such as MCP Design component APIs that resist misuse by AI and human developers Write high-quality, performant frontend code with React and TypeScript Partner with design, product ...

augment your end-to-end design and development process. Expertise with modern AI technologies and ability to apply them to design problems (e.g., MCP, Claude Code, Codex, Skills).Experience shipping production-ready experiences and influencing technical and design choices across teams. Strong understanding of user-centered design principles ...

match you to the right one: Fluency with AI-assisted development, and interest in scaling agent-assisted workflows across the team (agentic CLI tools, MCP, skills, APIs) to amplify delivery. Familiarity with confidential computing technologies: TEEs, AMD SEV, Intel TDX, or Confidential Containers (CoCo). Experience building SaaS or PaaS ...

About the team The Roku Entertainment Assistant team builds conversational AI experiences used across millions of Roku devices. The team works across fulfilment ranking, model delivery, offline and online evaluation, low-latency services, observability and product quality. Its published work includes shared model-serving and MLOps paths, automated … their impact. We value your AI skills if you 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 ...

applications inside client systems, ensuring solutions meet enterprise requirements for performance, security, and reliability. Develop technical assets - Create reusable, production‐ready artefacts including MCP servers, sub‐agents, agent orchestration frameworks, and evaluation tooling that can be deployed across client workflows. Support enterprise deployments - Play a key technical role in rollouts … Identify patterns and scale - Recognise repeatable deployment patterns across engagements and contribute those insights back to Accenture's I&E FDE practice and our model provider partners to continuously improve our delivery playbook. Maintain cutting‐edge expertise - Stay ahead of the curve on LLM capabilities, agentic frameworks, evaluation methodologies ...

systems in production or near‐production settings. Experience with generative AI systems, LLM‐enabled applications or evaluation pipelines. Experience with cloud platforms, MLOps tooling, model serving or platform engineering. Advanced use of Linux, Docker, version control, CI/CD and service‐oriented deployment practices. Experience working across the lifecycle … government or academia. Experience in regulated industries such as insurance, financial services, public sector or national‐scale infrastructure contexts. Familiarity with agentic systems design, MCP/A2A protocols, or inference‐time privacy controls. Familiarity innovating with agentic‐driven workflows and toolsets for both research and prototyping tasks, such as Claude ...

Senior AI Engineer (BioTech/Pharma) | Outside IR35 Contract £600 - 700pd | Hybrid, Oxford | 6 Months Harvey Nash are working with an exciting consultancy who are looking to bring on a highly experienced AI Engineer to ...

reusable AI services. Establish scalable, secure, and compliant architecture patterns for Agentic solutions using industry standard frameworks. Provide hands-on technical leadership across MCP, Python, TypeScript, React, APIs, OpenShift, Kubernetes, and CI/CD engineering practices. Build AI solutions including Agents, chatbots, RAG & Knowledge platforms, Skill based agents, workflow automation … enabled developer experiences Define engineering standards for prompt engineering, skill engineering, model evaluation, observability, guardrails, red teaming, hallucination detection, and responsible AI adoption. Partner with engineering leads, product owners, cybersecurity, governance, risk, platform, and UI/UX teams to align technical direction with strategic business outcomes. Mentor senior engineers ...

Associate Machine Learning Quality Engineer to join the Corporate Engineering AI team. You will help define evaluation frameworks and build automated test pipelines for MCP tools and Skills. You will collaborate with ML engineers to integrate evaluation hooks, address agentic risks, and provide testing evidence for PTB and PTO, ensuring ...