Senior AI Engineer (AI Platform)

Description

The role sits in the AI Platform team, which builds the shared foundations that let teams across the company use AI, with the Agentic AI Platform initiative as the main focus alongside other platform capabilities as they develop.

It is a platform role, not tied to a single business use case. You will create shared capabilities, standards, reusable templates and reference implementations for agents on Azure, so that engineering teams can build, ship and run agents safely at scale. You will work with Product, Cloud Infrastructure, Security and engineering teams to make AI secure, observable, reliable and reusable by default.

You will also help build the production base needed to run AI reliably, covering LLMOps, model access, prompt and agent lifecycle, evaluation, observability and secure enterprise integration.

This is hands-on engineering. Other teams will use what you build, which helps set consistent ways of building and running AI at scale.

The company is the company, an online fashion retailer.

Responsibilities

• Design and build shared AI platform capabilities on Azure, focusing on agent runtimes, orchestration and tool integration.
• Help define how agents are built, connected and run across the organisation as part of the Agentic AI Platform initiative.
• Create and maintain standard templates, reusable components and reference implementations for LLM and generative AI workflows so teams can use the same patterns.
• Build reusable patterns for prompt design, tool calling, multi-step agent flows, retries and failure handling.
• Help set engineering standards and best practices for production AI work across the company.
• Implement secure, governed access to LLMs and enterprise tools using APIM, platform gateways, Entra ID, RBAC and managed identities.
• Contribute to LLMOps and model runtime patterns, including standard approaches to model access, routing, caching, token optimisation and cost-aware usage controls.
• Support lifecycle and evaluation practices for agent configurations, prompts and AI workflows, covering testing, controlled change and release readiness.
• Design secure tool-access patterns for agents, including MCP and tool abstraction, credential management and enterprise API integration.
• Contribute to AgentOps and GenAIOps capabilities such as telemetry, run history, task outcomes, error analysis and feedback loops.
• Contribute to reliability patterns for production AI systems, including latency monitoring, alerting, scaling and operational readiness.
• Apply CI/CD and software engineering best practices to AI platform and agent components.
• Make AI systems measurable, debuggable and auditable by default, using logs, metrics and traces.
• Work with Cloud Infrastructure and Security teams to design Azure environments that are secure, scalable and cost-effective.
• Help other engineering teams adopt the platform and move AI capabilities from experiment to reliable production.

Requirements

• Significant experience as an AI Engineer, AI Platform Engineer, Software Engineer or a similar role, delivering production-grade AI systems.
• Hands-on experience with LLMs, generative AI and agent-based systems in live production environments.
• Experience building reusable AI capabilities, platforms, frameworks, templates or services that other engineering teams can adopt.
• A solid grasp of the full AI lifecycle, from experimentation through deployment and operation.
• Practical knowledge of production LLM or GenAI runtime concerns such as model access, routing, caching, token usage, cost optimisation and reliability.
• High proficiency in Python, with experience building APIs and service-oriented systems.
• Experience with CI/CD pipelines, automated testing and versioned deployments for AI or platform components.
• Practical experience with observability tooling (logging, metrics, tracing and alerting) and using telemetry to improve reliability and performance.
• Hands-on experience with Azure cloud and AI services.
• Experience with Azure AI Foundry is preferred. Strong hands-on experience with comparable GenAI or agent platforms, and the ability to apply those patterns within Azure, is also considered.
• Experience with Azure API Management (APIM) is preferred, particularly as a governance or integration boundary.
• Familiarity with AgentOps, MLOps or GenAIOps concepts, including monitoring, evaluation and feedback loops.
• Experience setting up or contributing to engineering standards, reusable patterns or best practices for AI development.
• Strong collaboration skills and the ability to influence platform standards and enable other teams.
• A pragmatic, engineering-led approach to responsible and ethical AI, focused on safety, reliability and trust.
• Additional information is provided in the posting.

Conditions

25 days of paid annual leave, plus an extra day to celebrate a special moment.

Equal opportunities: the company is a Disability Confident Committed employer, so candidates can ask the Talent team for reasonable adjustments at any stage of recruitment.

Benefits

• Employee discount.
• Employee sample sales.
• Discretionary bonus scheme.
• Private medical care scheme.
• Flexible benefits allowance, which you can take as extra cash or spend on other benefits.
• Personalised learning and in-the-moment experiences to help you thrive in your role.