Tesco Media & Insight Platform is a partnership between Tesco, the UK's largest grocery retailer, and dunnhumby. Fueled by first‑party behavioral data from over 23 million Clubcard holders, we help brands understand consumer behaviors and reach the right customers, at the right time, with the right message across the full marketing funnel. Our closed‑loop measurement connects what customers see with what they buy, helping brands Shape What Britain Buys and maximize the impact of every pound of media investment.
Roles and Responsibilities
As a Senior AI Engineer, you will be a hands‑on technical contributor designing, building and operating production‑grade GenAI and agentic AI solutions that power Tesco Media & Insight Platform's global products and services. You will work closely with the AI Engineering Manager, Product, Data Science and Engineering teams to turn business problems into secure, scalable, observable AI systems that deliver measurable value for brands and shoppers.
- Design and implement GenAI and agentic AI solutions on GCP, leveraging Vertex AI (models, endpoints, pipelines, vector search/RAG, Agent Builder) and core GCP services.
- Build AI agents and multi‑step agentic workflows, including tool calling, orchestration, and integrations with internal and external systems.
- Contribute to the design of MCP servers and agent‑to‑agent / agent‑to‑application protocols to enable safe, reliable automation of retail media and insight use cases.
- Work with the AI Engineering Manager and architects to define solution designs, interface contracts and non‑functional requirements (security, reliability, performance, cost).
- Implement security, privacy and governance controls in AI solutions, including safe prompt and tool design, data protection, secrets management and access control.
- Apply DevOps/MLOps practices: contribute to CI/CD pipelines for models, prompts and agents; use infrastructure as code; support environment management and automated testing.
- Implement observability for AI systems: instrument prompts, model calls, tools and agents with tracing, metrics and logs; build and maintain dashboards and alerts.
- Help define and run AI testing and evaluation strategies, including automated tests, offline and online evaluation, red‑teaming, regression suites and human‑in‑the‑loop review flows.
- Collaborate with Retail Media and Insight teams to understand use cases and data, and translate requirements into concrete AI components and services.
- Write high‑quality, well‑tested code in Python (and, where relevant, TypeScript/Java or similar) following team standards for readability, performance and reliability.
- Participate in code reviews, design reviews and incident post‑mortems, and contribute to continuous improvement of our AI engineering practices.
- Stay current on advances in LLMs, agentic frameworks and cloud AI services, and bring forward ideas for how they can be applied to Tesco Media & Insight Platform.
What you'll need to succeed in the role
- Strong experience in software/data/ML engineering, with hands‑on delivery of AI/ML or LLM‑based solutions into production (not just prototypes).
- Practical experience on GCP and Vertex AI, including deploying models, building pipelines, and implementing RAG/vector search‑based solutions.
- Solid understanding of LLMs and foundation models: transformers at a high level, tokenization, embeddings, context windows, RAG, and the trade‑offs between fine‑tuning, adapters and prompt‑based approaches.
- Hands‑on experience building agentic workflows or AI agents (e.g. tool‑augmented chat, multi‑step workflows, or multi‑agent systems) using one or more modern frameworks or platforms.
- Good grasp of security and safety for AI systems, including prompt and tool design to reduce hallucinations and prompt injection, safe handling of sensitive data, and application‑level guardrails.
- Experience with DevOps/MLOps practices: CI/CD, version control, automated testing, infrastructure as code, monitoring and incident handling in a cloud environment.
- Strong programming skills in Python and experience building and consuming APIs; familiarity with microservices and event‑driven architectures is a plus.
- Ability to design and run evaluation and experimentation for AI features, including quantitative and qualitative measures and, where appropriate, human‑in‑the‑loop review.
- Strong problem‑solving skills, attention to detail, and a willingness to take ownership of complex technical challenges.
- Clear, proactive communication and the ability to collaborate effectively with product managers, data scientists, engineers and commercial stakeholders across locations.
