> Markdown version of [/jobs/ext/3286528-senior-ai-engineer](https://www.wearedevelopers.com/jobs/ext/3286528-senior-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior AI Engineer - **Company:** RightShip - **Location:** London, UK - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Microsoft Azure, Code Review, Data Security, Graph Database, Python (Programming Language), Neo4j, Regression Testing, Search Technologies, Software Engineering, Pytorch, Large Language Models, Multi-Agent Systems, Build Management, Data Lakes, Information Technology, Free and Open-Source Software, Machine Learning Operations, Software Version Control, Databricks - **Published:** September 22, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=12d6e69df69b42b9 ## About the Role * Bachelor's or Master's degree in Computer Science, Data Science, Engineering, Mathematics or a related field, or equivalent practical experience. * 5+ years of hands-on AI/ML or software engineering experience, including LLM-based applications that have reached production. * Strong Python and software engineering fundamentals: testing, packaging, version control, code review and CI. * Demonstrated experience building agentic systems and RAG pipelines with LangGraph (and LangChain or similar), including tool use, state management and structured outputs. * Experience designing and running LLM evaluations: building evaluation datasets, choosing metrics, LLM-as-judge, regression testing and monitoring quality in production. * Practical knowledge of embeddings, vector search and hybrid retrieval. * Experience deploying AI workloads on Azure, for example Azure OpenAI / AI Foundry, Azure AI Search and Functions or Container Apps. * Comfortable working in an experimental setting where requirements are loosely defined and part of the job is working out what to build. * Excellent communication skills, including explaining technical trade-offs to non-technical colleagues. Desirable * Experience with Databricks (MLflow, Delta Lake, model serving). * Solid ML fundamentals; exposure to PyTorch or classical ML is useful but not central to this role. * Experience with multi-modal models, particularly document and image understanding. * Familiarity with graph databases (Neo4j, Cypher) or knowledge graphs. * Experience in maritime, shipping, logistics or another safety- or compliance-driven domain. * Open-source contributions or a public portfolio of work. ## Description We are growing the AI capability within our Product team and are looking for a Senior AI Engineer to join us in London. This is an applied, experimental role that sits inside the Product team rather than a central engineering function. You will work directly with Product Managers to understand the problems our customers face, shape those problems into candidate AI solutions, and prove or disprove them quickly through prototypes, experiments and rigorous evaluation. What works, you carry through to production-ready code, with the tests, evals and documentation our engineering teams need to take it on and run it at scale. You will work across LLM-based applications, agentic systems and retrieval over structured and unstructured maritime data, primarily on Azure and Databricks, and you will help set how the AI team builds, evaluates and hands over AI at RightShip. A large part of the job is working out what is worth building, so you should be comfortable with ambiguity and confident recommending that an approach is dropped when the evidence says so. Major Responsibilities * Work directly with Product Managers to gather and refine requirements, and translate them into candidate AI solutions with clear success criteria and evaluation plans. * Rapidly prototype and experiment with LLM-based applications, agents and retrieval pipelines to establish whether an idea works before it is committed to the roadmap. * Propose and document solution architectures, covering model choice, orchestration, data access, guardrails, and cost and latency trade-offs. * Design and build AI evaluation suites, offline and online, that define what good looks like for each feature and can be run in production to monitor quality over time. * Produce production-ready code with tests, evals, documentation and observability, hand it over to the engineering teams for productionisation, and support them through that transition. * Build and maintain retrieval and embedding pipelines over maritime data such as inspection reports, vessel records, documents and the RightShip knowledge graph. * Apply Responsible AI practice: traceability, guardrails, assessment of failure modes and bias, and alignment with RightShip's AI risk management framework. * Present experimental results and recommendations clearly to product, engineering and senior stakeholders. * Contribute to the AI team's shared tooling, patterns and standards; review code and share knowledge with colleagues. * Keep abreast of developments in models, agent frameworks and evaluation methods, and assess which are worth adopting.