As a Senior AI Engineer, you will be part of the AI Platform team, helping to build and scale the shared foundations that enable AI capabilities across ASOS. The primary focus of this role will be contributing to the Agentic AI Platform initiative, alongside other core AI platform capabilities as the platform evolves.
This role is focused on the platform layer, rather than individual business use cases. You will design and implement shared capabilities, standards, reusable templates and reference implementations for agentic AI on Azure, enabling engineering teams across ASOS to safely design, deploy and operate AI agents at enterprise scale. Working closely with Product teams, Cloud Infrastructure, Security and engineering teams, you will help establish the patterns and capabilities that make AI secure, observable, reliable and reusable by default.
You will also contribute to the production foundations needed to operate AI capabilities reliably, including LLMOps, model access patterns, prompt and agent lifecycle practices, evaluation, observability and secure enterprise integration.
This is a hands-on engineering role where the capabilities you build will be used by other teams across ASOS, helping to establish consistent engineering practices for building and operating AI at scale.
Designing and building shared AI platform capabilities on Azure, with a strong focus on agentic AI patterns such as agent runtimes, orchestration and tool integrationContributing to the Agentic AI Platform initiative, helping define how agents are built, integrated and operated across the organisationDesigning and maintaining standardised templates, reusable components and reference implementations for LLM and Generative AI workflows, enabling engineering teams to adopt consistent patternsBuilding reusable patterns for prompt design, tool calling, multi-step agent flows, retries and failure handlingHelping establish engineering standards and best practices for production AI development across ASOSImplementing secure, governed access patterns for LLMs and enterprise tools using APIM, platform gateways, Entra ID, RBAC and managed identitiesContributing to LLMOps and model runtime patterns, including standard approaches for model access, routing, caching, token optimisation and cost-aware usage controlsSupporting lifecycle and evaluation practices for agent configurations, prompts and AI workflows, including testing, controlled change and release readinessDesigning secure tool-access patterns for agents, including MCP/tool abstraction, credential management and enterprise API integrationContributing to AgentOps and GenAIOps capabilities, including telemetry, run history, task outcomes, error analysis and feedback loopsContributing to reliability patterns for production AI systems, including latency monitoring, alerting, scaling considerations and operational readinessApplying CI/CD and software engineering best practices to AI platform and agentic componentsEmbedding observability by default, ensuring AI systems are measurable, debuggable and auditable through logs, metrics and tracesWorking with Cloud Infrastructure and Security teams to design secure, scalable and cost-effective Azure environmentsWorking with other engineering teams to enable adoption of the platform, helping teams move AI capabilities from experimentation into reliable production
