Senior Applied AI Engineer

In this role you will own the AI behavior of production systems for public sector clients, shaping agents, model integration, and backend services. You will lead delivery for your workstream and serve as the technical client contact on live data performance. You will design evaluations to connect model behavior with real-world outcomes and implement guardrails, observability, and tooling to scale with client needs. You will collaborate across teams to drive reliable, compliant AI solutions that deliver tangible public-sector impact. This is a hands-on, client-facing position with a focus on end-to-end production readiness and continual improvement.

• Own the AI layer of production systems for public sector clients, including agents, model integration, and backend services they run on
• Build production agents from established architectural patterns, with reliable tool calling, guardrails, and observability
• Select and adapt evaluation methods, and design new evaluations for client-specific risks
• Apply context engineering, retrieval-augmented generation, model adaptation, or inference optimisation
• Investigate regressions in the systems you own, lead root-cause analysis, and implement preventative changes
• Lead project planning for your workstream and manage client expectations on scope, risk, and delivery
• Codify recurring client work into reusable tooling, evaluation components, or guidance that other engineers adopt
• Mentor engineers through code review, pairing, and delegated ownership

• Backend engineering experience, with a track record of taking AI/ML systems into production and keeping them reliable
• Ownership of the AI behaviour of a production system end to end, rather than delivering a component scoped by another team
• Hands-on evaluation design that ties model behaviour to real-world outcomes, used to catch regressions
• Comfort working directly with clients, including explaining model behaviour and trade-offs to non-technical stakeholders
• Practical knowledge of handling regulated or sensitive data and designing for auditability; sovereign or on-premise deployment experience is valuable
• Experience leading root-cause analysis on production AI or ML systems

• Client-facing communication
• Ownership and accountability
• Cross-functional collaboration
• Backend engineering
• Production AI/ML systems reliability
• Evaluation design linked to real-world outcomes