Senior AI Engineer

• Build AI-enabled tools that help Search teams find problems, test changes and measure relevance more quickly
• Design and build AI-enabled features that turn search behaviour, diagnostics and quality data into prioritised, actionable insights
• Build backend services and APIs for tools that collect and combine human relevance judgements
• Turn the existing offline evaluation tool into on-demand environments that developers can run in the CI/CD pipeline
• Define and automate checks on the accuracy and reliability of AI features, including LLM-based relevance judgements
• Work with product, design, data science and Search colleagues to turn prototypes into production releases
• Integrate with existing client platforms and APIs
• Monitor quality, latency and cost, and document decisions and trade-offs
• Share work early through documentation, demonstrations and incremental pull requests
• Own deliverables within agreed architecture and engineering practices
• Communicate decisions, risks and trade-offs clearly
• Assess the quality of AI-generated outputs with Search and data science colleagues
• Experiment quickly, test assumptions against real data and iterate using evidence
• Balance exploration with delivery and avoid unnecessary complexity early on
• Design for trust, clarity and adoption by tool users
• Recognise when deterministic rules, traditional machine learning or human review are more appropriate than an LLM

• Five or more years of professional experience across software engineering, data engineering, machine learning or applied AI
• Hands-on experience building LLM applications in production, including prompt design, structured outputs and API integration
• Understanding of embeddings, semantic search and hybrid retrieval, and their trade-offs against lexical search
• Ability to compare models and approaches on quality, latency, security and cost
• Experience building offline evaluations and benchmarks with labelled datasets, and using LLMs as judges calibrated against human labels
• Understanding of ranking metrics such as nDCG, Precision at K and MRR, and of inter-rater agreement
• Awareness of hallucination, bias, drift and privacy risks, and experience designing human review
• Strong SQL skills and experience with large analytical datasets
• Familiarity with medallion architectures and integrating AI with data pipelines and APIs
• Strong Python skills, including maintainable backend services and APIs
• Good testing discipline across application, data and AI components
• Experience with CI/CD, containerisation and cloud infrastructure, ideally Microsoft Azure
• Demonstrated experience delivering AI-enabled systems beyond isolated proofs of concept
• Proven ability to ship iterative, user-focused solutions with appropriate attention to reliability and safety
• Strong written and verbal communication skills, including explaining technical choices and evaluation results to non-technical stakeholders
• A collaborative approach to multidisciplinary product delivery
• Nice to have: Experience in retail or ecommerce search, including product taxonomy and long-tail queries
• Nice to have: Hands-on experience with Elasticsearch or another production search platform, or with a vector database
• Nice to have: Experience building offline evaluation or A/B testing tooling for search or recommendation
• Nice to have: Experience building human annotation or rating tools
• Nice to have: Experience with event streaming, such as Kafka, or clickstream and web analytics data

• Highly competitive compensation package
• Medical insurance
• Flexible remote work
• Opportunity to join an organization with triple-digit growth
• Opportunity to form part of a multicultural community of tech experts