Customs AI Integration & Automation Engineer (UK)

Main mission

You will take our AI stack and lead its development and customisation for the market. This is a builder and do-er role. You will design, test and implement practical and compliant agentic AI solutions on top of foundation models document understanding, classification support, retrieval over our own procedures and tariff material, and agents that carry multi-step operational work end to end. You are not being asked to train models from scratch. You are being asked to make models that already exist behave reliably enough that operations staff trust them with customs declarations, where being wrong has consequences. Working closely with Operations, Transformation, IT and Group teams, you will turn business needs into scalable solutions.

Key responsibilities

• Develop and customise AI solutions for the market, from prototype through to production ownership.
• Be curious and prepared to self-learn to use generative-AI to build agents that make a difference to our business
• Identify automation and decision-support opportunities across customs and business processes, and size them honestly before building.
• Design solutions using generative AI and large language models — retrieval, tool calling, structured extraction from customs documentation, and agentic workflows where they genuinely fit.
• Own the evaluation.
• Define how we know a solution is working before it ships, and how we know a change has not made it worse.
• This is treated as core to the role, not an afterthought.
• Manage pilots and implementation, and set the criteria for killing a pilot as clearly as the criteria for scaling it.
• Monitor performance, inference cost, latency and business impact.
• Collaborate with local teams, Group functions and technology partners.
• Contribute to privacy, security and AI governance compliance, working with Group Legal and IT Security.
• You should understand how the EU AI Act applies to what you build, and be able to produce the documentation that goes with it. .

Key skills

• Essential
• 1-2 years AI engineering, software engineering or intelligent automation, including LLM or AI features that real users depended on.
• Strong Python and SQL, with production code ownership.
• Not familiarity.
• Demonstrable experience integrating large language models into production systems — prompt and context design, retrieval-augmented generation, structured output, and handling failure gracefully.
• Practical experience with at least one major cloud AI platform (Azure AI, AWS Bedrock, or Google Vertex).
• Solid full stack backend engineering fundamentals — APIs, data pipelines, testing, CI/CD.
• Most of this job is
• Strong communication skills — you will spend real time with operations staff who are experts in customs and not in AI.
• Professional fluency in English.
• Desirable
• Evaluation engineering — building eval harnesses and regression suites for non-deterministic systems, LLM-as-judge approaches, and human-in-the-loop review design.
• This is the single strongest signal we look for and we will weight it heavily.
• Context engineering — designing and version-controlling what a model 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 in your first year
• By month three — You understand our customs processes well enough to challenge what we ask for, and you have shipped one small, useful thing.
• By month six — At least one AI solution is live, measured against a baseline, and demonstrably better than what it replaced.
• By month twelve — There is a working evaluation process others can use, a ranked pipeline of next opportunities, and at least two colleagues outside IT operating what you have built without you in the room.

What the company offers

• A key role in shaping AI capabilities.
• The opportunity to build solutions with direct business impact, on real operational volume rather than pilots that never leave the lab.
• An international and fast-evolving environment, with peers in other Customs Support Group markets working on the same problems.
• Professional growth opportunities, including a budget for conferences, certification and model/compute costs for your own experiments.
• Permanent role.
• Hybrid working.
• How to apply Send us your CV and a short note a few paragraphs is plenty describing one system you have put in front of real users.
• We are most interested in what went wrong with it and what you did about that.