14 of 14 Permanent Model Context Protocol Jobs in the South West

large language models (LLMs) and generative AI concepts, including AI agents, prompt engineering, context management, and Model Context Protocol (MCP), including MCP Apps and their UI capabilities Mastery of AI tools, in particular Claude Desktop and Claude Code, with day-to-day use to work faster … agents, defining how each capability is exposed and packaged for agent-based consumption Recommend the best distribution channel for each business service, evaluating MCP, MCP App, and other options based on customer fit, reach, and technical trade-offs Build prototypes to test in front of internal and external clients, validating ...

approval gates so developers can verify and correct agent output before it is merged. Integrate tools and data sources into the agents via MCP (Model Context Protocol). Set up evaluation, guardrails and tests to catch incorrect output early. Work alongside engineering team's and upskill them ...

APIs using clean and maintainable architecture patterns. Design and optimise PostgreSQL databases, queries and migrations. Integrate AI capabilities into applications using agent frameworks and MCP concepts. Write high-quality code and carry out peer code reviews. Create and maintain unit and integration tests. Manage code using Git and CI/ ...

AutoGen, Claude Agent SDK, OpenAI tooling or custom orchestration frameworks . Integrate leading and self-hosted LLMs with tools, data and external systems using MCP and custom connectors . Implement RAG solutions using vector databases and hybrid retrieval where appropriate. Work across relational, document, key-value and graph databases depending … genuine use case. Production & Engineering You'll own solutions all the way into production, including: Infrastructure and deployment. AI evaluation and testing frameworks. MCP server implementation. Cloud deployment across AWS, Azure, Cloudflare or Vercel . Docker, Kubernetes and/or serverless architectures. TDD and robust software engineering practices. Security, secrets ...

multi-tier software application development (Java, Python, JavaScript, C++, etc) Database technologies & ORM (Elastic, MySQL/MariaDB, SQL*Server, etc) Spec-driven software development & MCP use (Kiro, Claude, etc) Source-code control (Git & Git-based technologies e.g. GitOps) CI/CD platforms (GitLab, Jenkins) Configuration management & IaC frameworks (Terraform, Ansible ...

relationships and communicate technical recommendations, risks and progress to stakeholders. Drive the adoption of GenAI within Quality Engineering, including tools such as Playwright with MCP, GitHub Copilot and Claude. Contribute to internal QE communities, standards and best practices. What were looking for Strong hands-on experience in Quality Engineering ...

React: the agents people talk to and the apps they click through, built in TypeScript. And you don't stop there. From API and MCP design to infrastructure on Vercel, AWS, Supabase, and BigQuery, plus the agents that work across the stack, you own complete features end to end, including ...

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 ...

every single requirement, please apply! You still may be a great fit for this role or other open roles. We are seeking candidates who model our values: invest in every relationship, lead with curiosity, champion diverse perspectives, turn inputs into actions, and uphold trust through integrity. Skills and Competencies … Hands-on experience building AI/ML applications (RAG, agent frameworks, MCPs, skills, harnesses) and taking them to production or in platforming (LLM or MCP gateway, agentic runtime, auth, data retrieval, eval tooling) Experience operating production distributed systems on AWS/Azure, with a strong grasp of reliability, observability ...

across the modern AI engineering stack - harness engineering, skills and tool building, agent workflows and orchestration, agent hosting and sandboxing, guardrails, evals, RAG and context engineering, and tokenomics (cost, latency, model selection). Production-grade LLM system experience is the core requirement. You will work on three types … integrate with both is required; existing expertise is a bonus rather than a requirement. Experience with agent hosting and sandboxing platforms, LLM or MCP gateways, or agentic workflow orchestration tooling. Experience in financial services or another regulated environment. Experience deploying models built by a data science team into customer-facing ...

design decisions, and assess technical risk Deep expertise in enterprise AI applications built on large language models, including agents, retrieval augmented generation, orchestration frameworks, model optimization, and evaluation frameworks … Hands-on experience building AI/ML applications (RAG, agent frameworks, MCPs, skills, harnesses) and taking them to production or in platforming (LLM or MCP gateway, agentic runtime, auth, data retrieval, eval tooling) Experience running AI systems in production at scale, including observability, cost and capacity planning, regression detection ...

team from day one - owning delivery, growing the function, and proving the value. You'll work daily with Claude, Claude Code, MCP, and LangChain to build production-grade agents and automations that internal teams actually use. Your team builds automations and agents for internal use and serves as internal consultants … Help refine AI training for the wider organisation, including Software Engineering teams Technical Environment AI & Agentic Frameworks: Claude, Claude Code, Anthropic tooling, LangChain, LangGraph, MCP, multi-agent orchestration, Google ADK (or similar agentic tooling) Automation & Prototyping: Scripting, workflow tools, AI-assisted development, rapid prototyping (Vercel/Railway) Enterprise Tooling: Identity ...

specialization in at least one AI platform ecosystem — Google (Gemini Enterprise), Anthropic (Claude), or OpenAI — deep enough to advise credibly on platform strategy. Understand context engineering well enough to shape how clients connect AI to their data, documents, and systems. Lead and develop the US consulting team: recruiting, mentoring … Preferred Experience Vertical expertise in CPG, retail, financial services, healthcare, or telecom. Experience taking clients from AI experimentation to scaled, governed adoption. Familiarity with context engineering concepts: RAG, semantic layers, knowledge bases, MCP. An existing network and reputation in the US data & AI market. Why you should join ...

delivery of Quality Engineering strategies. Manage project-level client relationships and communicate progress, risks and recommendations. Drive adoption of GenAI tooling, including Playwright with MCP, GitHub Copilot and Claude. Contribute to internal QE communities, standards and best practices. Experience you'll need as a Quality Engineering Manager Several years experience …/TypeScript, Python, Java or C#. Experience building and assessing automation frameworks, not just using them. Hands-on experience with GenAI in a QE context and AI-assisted coding tools. Experience defining tooling strategies and conducting QE assessments. Experience leading or mentoring QE or automation engineering teams. Strong client ...