Salary: £37,000 - 52,000 per year Requirements: 5 years of experience in a development role is essential. Degree-level qualification is desirable. Hands-on experience with generative AI and large language models. Experience with RAG, prompt engineering, and evaluation techniques. Experience with AI infrastructure, including vector stores, embeddings, and model serving. Experience with AI agent frameworks and orchestration. Understanding of embeddings and vector search. Experience using Claude Code or an equivalent AI coding assistant. Experience designing secure AI solutions. Understanding of responsible AI principles. Demonstrable AI engineering skills. Experience with agentic tooling is desirable. Knowledge of the facilities management domain is desirable. Background in domain-driven design, event-driven systems, or clean architecture is desirable. Experience with TypeScript, Python, React, and Node.js. Experience with the Microsoft .NET stack, SQL Server, and NoSQL databases such as Cosmos DB. Experience with REST API design and integration. Experience with design patterns and clean architecture. Experience with Git, Azure DevOps, CI/CD pipelines, and infrastructure as code. Proactive, self-driven, and able to work independently or as part of a team. Focused on outcomes rather than outputs. Excellent verbal and written communication skills. Pragmatic and flexible attitude. Excellent interpersonal skills. Strong attention to detail. Mentoring and coaching skills. Responsibilities: We design and implement secure, scalable LLM-powered applications using modern generative AI architectures. We collaborate with product, data, and operations teams to identify problems and explore how AI can solve them. We use AI coding assistants such as Claude Code or equivalent in our day-to-day development workflows to improve efficiency, quality, and delivery speed. We optimise performance across latency, cost, accuracy, security, and reliability. We ensure all software aligns with our technical roadmap, development guidelines, and security standards. We troubleshoot, debug, and resolve technical issues across the product. We ensure code reviews and automated tests support quality assurance. We participate in refinement, planning, and delivery meetings. We lead the architecture and end-to-end development of AI solutions from prototyping to production. We collaborate with the Product team to identify suitable AI use cases and help them understand where AI can deliver business value. We work closely with IT Governance and Cyber Security teams to ensure our AI solutions are secure by design and that data is handled responsibly and ethically. We define technical standards, best practices, and engineering roadmaps for AI initiatives. We provide technical leadership and mentor developers. We stay current with AI advancements, evaluate emerging technologies, and assess their applicability to our product. We own the quality, reliability, and performance of AI systems, including monitoring, testing, and observability. We conduct security and architectural reviews and foster a culture of engineering excellence. We communicate technical trade-offs and progress clearly to technical and non-technical stakeholders. We evaluate and select AI frameworks, LLM providers, vector databases, and cloud infrastructure. We champion AI engineering across the team, using AI tools to move faster without sacrificing code quality, security, or maintainability. We support continuous improvement across everything we do. We help build a strong culture focused on transparency, collaboration, and high performance. We support other team members and answer questions. We take ownership of our personal objectives, team objectives, deadlines, and releases. We treat quality issues as unacceptable and work to rectify them promptly. Technologies: AI API Azure CI/CD Claude Code Cloud Cosmos DB DevOps Git Support LLM NoSQL Python REST React SQL Security TypeScript ASP.NET NodeJS Architect More: We are hiring for a full-time, permanent Lead AI Engineer based at our Glasgow Head Office, working 37.5 hours per week. In this role, we are building and delivering AI-powered solutions across the group, with a strong focus on production-grade systems that use LLMs reliably and cost-effectively. We offer the opportunity to bridge cutting-edge AI research with production engineering, lead technical direction, mentor a high-performing team, and help shape our organisations AI journey while working closely with product, data, operations, IT Governance, and Cyber Security teams. last updated 24 week of 2026