426 to 450 of 573 Model Context Protocol Jobs

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 ...

agents in the loop on every change. That's leverage, and it's a new attack surface: prompt injection against agent harnesses, untrusted MCP server outputs, IAM scope creep on agent-driven tooling, model and prompt supply chain. You'll own the security layer of our agent platform: sandbox … paths, KMS misuse, and the defences for each Incident response leadership end-to-end on a real incident (containment, eradication, forensics, write-up) Authoring MCP servers or custom agent tools with a security lens Product Security Engineer Job Description 3 Familiarity with AGENTS.md/CLAUDE.md patterns and skill authoring Cryptography ...

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 binds 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 ...

effectively. Задачи: Design, build, and operate core GenAI platform components, including an LLM routing gateway, vector search and RAG infrastructure, tool registry and MCP gateway, AI observability and evaluation tooling, and infrastructure for long-running agentic workflows; Own production-quality delivery of platform features from design through rollout, monitoring … asynchronous workflows, idempotency, consistency trade-offs, and designing for failure; Hands-on experience with LLM APIs or strong interest in learning about rate limits, context windows, multi-vendor routing, latency variance, and cost control; Security mindset for AI systems, including prompt injection risks, PII in logs, data leakage ...

testing, quality gates, and security and dependency hygiene. That now covers how we work with coding agents: the rules they follow, the skills and MCP integrations we build over our own systems, and the review process that holds quality as more code gets generated. You're the one who challenges … coding agents day to day and have a view on where they help and where they quietly cause damage. Experience writing skills, MCP integrations or agent conventions for a team is a strong plus. Security is instinctive for you. Secure-by-design services, authentication and authorisation done properly, tenant ...

development to improve speed and quality, and build the reusable pieces that let others do the same: Skills, slash commands, subagents, hooks, MCP integrations and per‐codebase agent guidance, tailored to each team’s stack and conventions. Apply the same tooling to the codebases you work in: raising test coverage … Experience extending those tools rather than just using them out of the box: authoring reusable agent extensions (Claude Code Skills, slash commands, subagents, hooks, MCP servers) and the project‐level guidance files (CLAUDE.md and equivalents) that make an agent effective in a specific codebase. Experience integrating LLMs or other models ...

data. Agentic AI & LLM Guardrails: Design and deploy scalable guardrails, robust sandboxing, and real-time monitoring controls for our extensive LLM ecosystem, including ADK, MCP, and autonomous agentic workflows. Collaborative Security Engineering: Partner with ML researchers and platform engineers to design and implement robust security controls across the entire … model inversion, data poisoning) and frameworks like OWASP Top 10 for LLMs or MITRE ATLAS.Agentic Frameworks Security: Proven experience securing agentic frameworks (ADK, MCP), agentic first infrastructure and implementing robust agent-to-agent (A2A) identity and access controls. Infrastructure Security: Solid proficiency in cloud platform security (GCP preferred), including ...

automation Hands-on experience with Claude Code (or equivalent agentic CLI tooling — Cursor, Codex CLI, Cline, Aider): writing custom skills, building subagent systems, implementing MCP servers, and authoring AGENTS.md/CLAUDE.md context files Platform-as-a-product mindset: builds reusable assets with their consumers in mind, prioritises discoverability … infrastructure patterns that form the core of the central platform’s offering Develop Claude Code (or equivalent agentic CLI tooling) skills, subagents, and MCP servers that become the standard AI tooling distributed to all client teams Implement golden path templates — project scaffolding, pipeline configuration, security guardrails, AI-native workflow defaults ...

teams and SaaS platforms, with autonomy supported by a US-based CEO and GTM. You will conduct live product demos, speak credibly about APIs, MCP, and integration architecture. #J-18808-Ljbffr ...

Experience architecting the data layer behind AI or analytics products in production. Informed views on the trade‐offs between fine‐tuning, RAG, and long‐context approaches, and how each changes data architecture … requirements, including context window economics and prompt caching. Familiarity with infrastructure as code, CI/CD, and observability for data platforms. Awareness of MCP and tool‐orchestration concepts and their implications for composable, data‐driven AI systems. Fluent use of AI‐assisted development tools (e.g. Claude Code, Cursor), with ...

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 ...

experience with AI Development Life Cycle practices and methodology. Orchestration: Production, hands-on experience with an agentic framework such as LangGraph, plus familiarity with MCP-based tool orchestration. Exposure to AutoGen, LlamaIndex, or CrewAI is a plus. Production Python engineering: Clean, modular, testable, maintainable code — you care about system reliability … much as model output. Evaluation & observability: Practical experience instrumenting tracing (LangSmith, Arize) and building CI/CD pipelines built specifically for LLMs. Engineering foundations: Distributed systems, scalable data pipelines (Kafka, SQL), and cloud-native infrastructure. Cloud-native deployment: Deep familiarity with shipping agentic workloads into production environments, ideally leveraging ...

experience with AI Development Life Cycle practices and methodology. Orchestration : Production, hands-on experience with an agentic framework such as LangGraph, plus familiarity with MCP-based tool orchestration. Exposure to AutoGen, LlamaIndex, or CrewAI is a plus. Production Python engineering : Clean, modular, testable, maintainable code — you care about system reliability … much as model output. Evaluation & observability : Practical experience instrumenting tracing (LangSmith, Arize) and building CI/CD pipelines built specifically for LLMs. Engineering foundations : Distributed systems, scalable data pipelines (Kafka, SQL), and cloud-native infrastructure. Cloud-native deployment: Deep familiarity with shipping agentic workloads into production environments, ideally leveraging ...

experience with AI Development Life Cycle practices and methodology. Orchestration : Production, hands‐on experience with an agentic framework such as LangGraph, plus familiarity with MCP‐based tool orchestration. Exposure to AutoGen, LlamaIndex, or CrewAI is a plus. Production Python engineering : Clean, modular, testable, maintainable code — you care about system reliability … much as model output. Evaluation & observability : Practical experience instrumenting tracing (LangSmith, Arize) and building CI/CD pipelines built specifically for LLMs. Engineering foundations : Distributed systems, scalable data pipelines (Kafka, SQL), and cloud‐native infrastructure. Cloud‐native deployment: Deep familiarity with shipping agentic workloads into production environments, ideally leveraging ...

work directly with client engineers and stakeholders, as an AI specialist. What you will be doing Building and shipping LLM-backed agents: tool use, MCP servers, retrieval, orchestration between specialist agents, evaluation and guardrails Working across cloud model APIs and locally hosted models, and making sensible calls about which … have not done one, we will support you through it Background in financial services, market data or another regulated, data-heavy domain Experience with MCP server development Experience with time series or analytical databases (kdb+/KDB-X, ClickHouse, Oracle) Python, Java and TypeScript Experience deploying models on-premise ...

with the modern LLM/agent toolkit — model APIs, prompting, tool use, RAG, and the patterns this fast‐moving ecosystem is converging on (MCP, agent frameworks, evals). You enjoy working closely with non‐engineers — you are the kind of person who'll sit with a scientist to understand … sustainable work-life balance and we are open to discussing flexible working arrangements. We are a hybrid team operating on a highly collaborative model that values synchronization and pair programming. You will be welcomed by a team of colleagues with decades of accumulated experience in their areas of expertise ...

with the modern LLM/agent toolkit — model APIs, prompting, tool use, RAG, and the patterns this fast-moving ecosystem is converging on (MCP, agent frameworks, evals). You enjoy working closely with non-engineers — you are the kind of person who'll sit with a scientist to understand … sustainable work-life balance and we are open to discussing flexible working arrangements. We are a hybrid team operating on a highly collaborative model that values synchronization and pair programming. You will be welcomed by a team of colleagues with decades of accumulated experience in their areas of expertise ...

review steadily upward. Pipeline Engineering Build and maintain the agentic pipeline: agent harness, blueprint engine interleaving deterministic steps (lint, build, git) with AI reasoning, MCP tool layer exposing internal APIs, warm sandbox pool, and retrieval over the codebase, tickets, and historical PRs. Own the economics of the pipeline: observability over … agent-proposed solution meets performance, scalability, and reliability requirements, and challenging designs that will not hold up under real workloads. Experience building agent infrastructure: MCP servers and tool layers, sandboxed execution, and CI/CD adapted for agent-driven workflows. Deep enough .NET/C# and SQL reading fluency ...

review steadily upward. Pipeline Engineering Build and maintain the agentic pipeline: agent harness, blueprint engine interleaving deterministic steps (lint, build, git) with AI reasoning, MCP tool layer exposing internal APIs, warm sandbox pool, and retrieval over the codebase, tickets, and historical PRs. Own the economics of the pipeline: observability over … agent-proposed solution meets performance, scalability, and reliability requirements, and challenging designs that will not hold up under real workloads. Experience building agent infrastructure: MCP servers and tool layers, sandboxed execution, and CI/CD adapted for agent-driven workflows. Deep enough .NET/C# and SQL reading fluency ...

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 ...

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 ...

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 ...

zero. Based in Oxford, you will work in a dynamic and growing engineering organisation that builds cloud-based software to track and model power grids around the world. Please note that we are open to considering candidates who require visa sponsorship (subject to eligibility and company approval). Department … infrastructure Desirable attributes Hands-on experience building LLM-based systems Experience testing non-deterministic systems Understanding of statistics and inferential methods LangGraph, RAG, MCP, MLOps, IaaC, AWS What we offer Some of the benefits we include are: Private Medical Insurance Dental Insurance Parental Support Salary-Exchange Pension Employee Assistance Programme ...

frontier of how AI-augmented engineering works in practice — pioneering workflows using Claude Code, Claude MPM, and Duetto's in-house MCP server platform across US and European engineering teams. What Makes Us Different? Duetto is the hospitality industry's leading revenue management platform, founded in 2012 by former Wynn … OpenTelemetry, Datadog, Prometheus, Grafana, and Sentry instrumentation. You'll pioneer AI-augmented engineering workflows using Claude Code, Claude MPM, and Duetto's in-house MCP server platform (82+ tools) — setting the standard for how AI-assisted development works across US and European engineering teams. You'll drive architecture decisions through ...

scale their impact. We value your AI skills if 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 … analysis, auto-triage of build/test failures).Establish policies and guardrails for AI usage in internal tools: data handling, prompt/response logging, model/provider selection, evaluation, fallback behaviors, and abuse prevention.Dev Productivity & Enterprise Tooling (Global Scale)Set technical direction and standards for the globally used developer ...