AI & Automation Engineer

Role Purpose

We’re excited to be hiring a hands-on AI Engineer to join a growing MSP that’s putting AI to work in the real world.

This role suits someone with 2–5 years’ experience who thrives in a scale-up environment, isn’t afraid to roll their sleeves up, and can take ideas from concept to live, production-grade systems. You’ll be designing, building, and shipping AI-powered platforms, APIs, and agentic automations that make a tangible difference – cutting manual effort, improving efficiency, and helping teams get more value from the tools they already use.

You’ll work closely with leadership and service desk teams, turning prototypes into reliable, maintainable solutions and helping shape how they’re packaged and taken to market. A strong focus is the Microsoft 365 ecosystem, so hands-on experience with Microsoft tooling in business environments is essential.

Key Responsibilities

AI Engineering & Solution Delivery

• Design, build, and deploy production-grade AI solutions for internal teams and client environments, from initial architecture through to deployment and ongoing monitoring
• Develop and maintain agentic AI systems, LLM-powered workflows, and orchestration pipelines that solve real operational challenges
• Engineer robust, well-tested APIs and backend services that expose AI capabilities reliably and at scale
• Evolve proof-of-concepts into production-ready solutions, with full consideration for reliability, observability, and maintainability

API Design & Backend Systems

• Design and build clean, well-documented APIs that integrate AI capabilities into existing business systems and workflows
• Implement robust error handling, rate limiting, logging, and versioning across AI services
• Ensure integrations are secure, performant, and aligned with best practices for data governance
• Work with external APIs and third-party services to compose multi-system AI solutions

CI/CD & DevOps for AI

• Own the full deployment lifecycle for AI services, from local development through to staging and production on Azure
• Build and maintain CI/CD pipelines for AI workloads, including automated testing, environment promotion, and deployment gates
• Implement monitoring, alerting, and rollback strategies to keep AI services reliable in production
• Apply sound engineering practices around configuration management, secrets handling, and infrastructure-as-code

Microsoft Ecosystem & Azure

• Design and deliver AI solutions built on Microsoft-aligned architectures, including Azure AI services and data platforms
• Integrate AI capabilities into Microsoft 365 tools such as SharePoint, Teams, Outlook, and the Power Platform
• Support clients with the rollout, adoption, and optimisation of Microsoft Copilot and other AI-enabled workloads
• Use Azure services, including Azure AI Foundry, to deliver secure, scalable, and well-governed AI solutions

Agentic AI & Orchestration

• Architect and build multi-agent systems where individual AI agents collaborate, delegate, and hand off tasks to complete complex, multi-step workflows
• Design agent orchestration layers that coordinate tools, memory, and decision-making – knowing when to route, when to escalate, and when to stop
• Build and expose reusable AI skills and tools that agents can discover and invoke, enabling modular, composable system design
• Develop and integrate MCP (Model Context Protocol) servers to give agents structured, governed access to external data sources, APIs, and internal systems
• Implement robust tool-use patterns: defining clear tool schemas, handling failures gracefully, and ensuring agents behave predictably in production
• Think carefully about agent reliability, observability, and safety, building systems with appropriate guardrails, logging, and human-in-the-loop checkpoints where needed
• Identify opportunities to deploy agentic workflows that replace manual, repetitive, or multi-system processes
• Balance autonomy with control,  building agents that are capable enough to be useful, and constrained enough to be trusted

Collaboration & Communication

• Work closely with internal teams and leadership to understand requirements and translate them into well-engineered solutions
• Document solutions thoroughly to ensure they are maintainable, transferable, and scalable
• Contribute to internal engineering standards, tooling choices, and approaches for AI development

Required Skills & Experience

Essential

• 2–5 years’ experience in an AI Engineering, Software Engineering, or Applied AI role
• Strong foundation in software engineering principles: clean code, testing, version control, source control, and system design
• Proven experience building and deploying production AI or LLM-powered applications
• Hands-on experience designing and building APIs (RESTful and/or event-driven)
• Solid understanding of CI/CD practices and cloud deployment on Azure
• Experience building agentic AI systems, multi-agent orchestration, or LLM tool-use pipelines
• Familiarity with MCP (Model Context Protocol) or similar patterns for giving AI agents access to external systems
• Comfortable working across the full delivery lifecycle, from architecture to monitoring in production
• Strong understanding of Microsoft 365 in a business environment

Technical Skills

• Programming: Python (essential); production-quality, well-tested code
• LLMs & Prompting: LLM APIs, prompt engineering, structured outputs, tool/function calling
• Agentic Systems: Multi-agent orchestration, agent frameworks (e.g. LangGraph, AutoGen, or similar), MCP server development, skill and tool design
• API & Backend: REST API design, async patterns, authentication, versioning
• DevOps: CI/CD pipelines, Docker, cloud deployment, monitoring and observability
• Cloud: Microsoft Azure data and AI services (essential)

Desirable

• Experience with Azure AI Foundry
• Familiarity with agentic frameworks such as LangGraph, AutoGen, Mastra, CrewAI, or similar
• Experience building or consuming MCP servers
• Familiarity with tools such as Claude Code, OpenAI Codex, or ElevenLabs
• Exposure to client-facing or go-to-market AI projects
• Examples of prior work – deployed AI projects or open-source contributions

What We’re Looking For

• An engineer first: someone who cares about code quality, system design, and getting things into production
• Genuinely excited by what AI can enable in the real world, not just what it can demo and an avid user of AI for coding itself
• Comfortable working across both technical and non-technical teams
• Able to balance experimentation with shipping – and knowing when each is appropriate
• Strong appetite for learning and keeping skills current as the technology evolves
• Thrives in a scale-up environment and is comfortable owning problems end-to-end

What Success Looks Like

• AI solutions that achieve strong adoption, reliability, and measurable commercial impact
• Well-designed APIs and services that other teams can confidently build on
• Agentic systems that handle complex, multi-step workflows reliably and safely in production
• CI/CD pipelines and monitoring that keep AI workloads stable and observable
• Clear reductions in manual or repetitive work across internal and client environments
• Successful progression of ideas from prototype to production and go-to-market
• Teams better equipped to use AI effectively within their day-to-day workflows

ITC Service Benefit Package

• Dedicated office desk – onsite
• 29 days holiday inc bank holidays + Christmas to New Year shutdown
• Salary sacrifice pensions scheme with a +3% employer contribution
• Paid approved training
• From year 1, access to our Assist to Buy Technology and Electric Vehicle salary sacrifice
• Access to our Employee Assistance Program
• Breakfast snacks and refreshments onsite
• From 6 months, Life Insurance for you, spouse and children (free)
• From year 1, Full cover health insurance + dental and optical cashback
• From year 2, of employment Years in Service (YiS), Salary Increases + 1 Day Holiday (to a max of 5 years)
• Working hours from 8am to 5pm, Monday to Friday, with up to 1 hour for break