1 to 25 of 66 Digital & IT Jobs

sees — retrieval strategy, memory, tool descriptions, and policy layers that constrain what an agent is allowed to do. Agent orchestration frameworks and standards (LangGraph, MCP, Temporal or equivalent), and experience with long-running or multi-step agent workflows. Observability and cost control for inference at volume. What success looks like ...

assumptions, risks, milestones, and dependencies Embed with customer teams to co-build agentic applications on the Claude developer platform Build technical artifacts evaluation frameworks, MCP servers, sub-agents, and deployment configurations tailored to the customer's stack What Success Looks Like Customers move from proof-of-value to production Engineering ...

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 ...

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 ...

ways to make the process better each time 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 ...

guide and review AI-generated code with confidence. Hands-on experience building agentic systems using frameworks such as LangGraph, Microsoft Agentic Framework, or MCP, with a solid understanding of LLM capabilities and risks. Experience designing and running experiments to validate ideas quickly, using technical prototypes, customer feedback, and lean startup ...

part of the role is engineering AI agents and agentic workflows. You will design how agents use trusted knowledge, approved tools, Model Context Protocol (MCP) services, approvals, human hand-offs and safe failure paths. You will ensure that evaluation, observability, identity, permissions and data boundaries are built into delivery rather … agents and agentic workflows using trusted knowledge, tools, actions, approvals, human hand-offs, evaluation and safe failure paths. • Design and implement integrations with approved MCP servers and lead development of MCP tools or services using secure, reusable patterns. • Integrate Power Platform and AI solutions with Microsoft 365, SharePoint, Microsoft Graph ...

agent AI systems across customer-facing and operational domains. Defining and owning Aviva’s canonical engineering patterns for applied AI, including orchestration architectures, context engineering, MCP integration, memory design, fine-tuning and multimodal systems. Building and maintaining a reusable library of agent tools, MCP servers, skills and shared engineering assets … design). Context & Retrieval: Advanced context engineering expertise, including multi-hop retrieval, knowledge graphs (Neptune/Nebula), structured memory injection and dynamic prompt construction. MCP & Tooling: Advanced knowledge of Model Context Protocol (MCP), designing and implementing server architectures for enterprise tooling integration. Model Fine-Tuning: Experience with model fine-tuning ...

Data 360, semantic search, and Knowledge libraries. System Interoperability: Architect REST API callouts, event-driven integrations, and MuleSoft platform pipelines, incorporating Model Context Protocol (MCP) standards. D. Testing, Security & Strategic Advisory Testing & Quality Assurance: Drive automated testing and multi-turn conversation tracing using the Agentforce Testing Center. Security & Guardrails: Design ...

Models (LLMs) and the trade-offs between latency, capability, cost, and model sizing. Awareness of emerging AI protocols and standards (e.g., Model Context Protocol [MCP], Agent2Agent [A2A]). Exposure to automated AI evaluation, output benchmarking, and testing tools for AI-driven capabilities. R&D at AVEVA Our global team ...

Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), agent orchestration, prompt engineering, and tool calling. Familiarity with AI standards such as Model Context Protocol (MCP) and Agent2Agent (A2A). Experience with tools for automated testing and evaluation of AI outputs Experience working in Agile teams and collaborating across global ...

Large Language Models (LLMs), Retrieval‐Augmented Generation (RAG), agent orchestration, prompt engineering, and tool calling. Familiarity with AI standards such as Model Context Protocol (MCP) and Agent2Agent (A2A). Experience with tools for automated testing and evaluation of AI outputs Experience working in Agile teams and collaborating across global ...

Tooling & Security • Support the secure adoption and scaling of AI tools across Bulk. • Manage AI platforms including Claude Code, GitHub Copilot, Codex-style tools, MCP servers, integrations and connectors. • Own user access, permissions and governance, applying least-privilege principles. • Support teams onboarding new AI technologies, balancing innovation and productivity with … security and compliance. • Develop appropriate controls as agentic AI, MCP and connector-based technologies evolve. About You You're probably already operating at strong 3rd Line Engineer level and looking for the opportunity to take broader ownership across infrastructure and cyber security. You enjoy getting hands-on with technology ...

setup, configuration, and maintenance of AI tooling across the business (e.g., Claude Code, Cowork, Codex-style coding/agent tools), including integrations, MCP server configuration, and connector management. Manage user access, permissions, and governance for AI tools, ensuring least‐privilege access and secure connector/integration setup. Partner with teams … conducting vendor security assessments. Experience setting up and administering AI coding/agent tools (e.g., Claude Code, GitHub Copilot, Codex) and their integrations, including MCP servers, connector permissions, and access management. Desirable Skills ITIL and project management certifications (e.g., Prince2). Advanced knowledge of infrastructure best practices and proactive problem ...

Clinical Operations team deliver faster, more consistent customer support. Cross-system integration. Build and maintain integrations across Box, JIRA, HiBob and other platforms, including MCP-based and Claude Code-driven automations to remove manual handoffs between teams. GxP-aware delivery. Ensure every automation touching a validated or GxP-relevant system … Prior experience in a regulated environment (GxP, ISO 27001, medical devices, or clinical trials). Familiarity with computerised system validation (CSV) concepts. Exposure to MCP, agentic automation patterns, or workflow tooling. Understanding of information security fundamentals (access control, data classification, least privilege). What can you expect from ...

build pipelines Software supply chain integrity Container security and governance AI/ML workload governance (where applicable) AI agent architecture patterns: isolated execution environments, MCP policy enforcement, model artifact provenance Partner with Sales Engineers and Post-Sales teams to ensure technical continuity without owning deal cycles. What We re Looking … packaging, dependency management, reproducibility, and governance considerations within containerized environments. Practical Experience with AI coding agent runtimes and sandboxed execution environments (e.g., agent isolation, MCP tool governance) Familiarity with Docker SBX and MCP Gateway as enterprise controls for agentic AI workloads Familiarity with secure software supply chain practices, including SBOM ...

create reusable components, improve developer tooling and documentation, support consuming teams, and help shape modern design-to-development workflows; using Figma, MCP integrations, agentic cloud workflows and AI-assisted engineering tools. This is not an "AI for AI's sake" role: the goal is practical engineering impact, better component reuse … they improve quality, speed, consistency, or developer self-service. Help make DDS documentation and component metadata more useful to humans and AI agents through MCP-ready context, examples, and clear constraints. Lead through senior engineering craft: architectural judgment, code review, mentoring, pragmatic delivery, technical clarity, and high-quality communication. Relocation ...

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 ...

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 ...

deploy, and operate production-grade AI systems with focus on reliability, scalability, and performance. Expertise in Agentic AI systems: RAG, prompt engineering, LLM integration, MCP, agentic workflows, model evaluation, fine tuning. Cloud infrastructure expertise in the deployment of AI apps (AWS preferred). Expertise in CI/CD best practice ...

deploy, and operate production-grade AI systems with focus on reliability, scalability, and performance. Expertise in Agentic AI systems: RAG, prompt engineering, LLM integration, MCP, agentic workflows, model evaluation, fine tuning. Cloud infrastructure expertise in the deployment of AI apps (AWS preferred). Expertise in CI/CD best practice ...

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 ...

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 ...

Implementing AI feedback loops, e.g. custom tests, linter, compilation etc. Experience with different AI coding tools e.g. Cursor, VSCode agents, Claude code, Codex etc. MCP: Experience developing servers and clients Experience consuming existing servers and clients e.g. Claude desktop, cursor, etc. AI feedback loops, agent observability and evaluation Experience with ...

Fluency 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 ...