We'reASOS, the online retailer for fashion lovers all around the world.
We exist to give our customers the confidence to be whoever they want to be, and that goes for our people too. At ASOS,you'refree to be your true self without judgement, and channel your creativity into a platform used by millions.
Everyone needs some help showing up as their best self.We'reDisability Confident Committed - let our Talent team know if you need any reasonable adjustments throughout the recruitment process
Job Description
As aSenior AI Engineer, you will be part of theAI Platform team, helping to build and scale the shared foundations that enable AI capabilities across ASOS. Theprimary focus of this rolewill be contributing to theAgentic AI Platform initiative, alongside other core AI platform capabilities as the platform evolves.
This role is focused on theplatform layer, rather than individual business use cases. You will design and implementshared standards, templates and reference implementationsfor agentic AI onAzure, enabling application teams to safely design, deploy and operate AI agents at enterprise scale. Working closely with Product teams, Cloud Infrastructure, Security and partners, you will help ensure AI capabilities aresecure, observable,reusableand governed by default.You will also contribute to theproduction foundationsneeded to operate AI capabilities reliably, includingLLMOps, model access patterns, promptand agentlifecyclepractices, observability and secure enterprise integration.
What you’ll be doing
- Designing and buildingAI platform capabilitieson Azure, with a strong focus on agentic AI patterns such as agent runtimes, orchestration and tool integration
- Contributing to theAgentic AI Platform initiative, helping define how agents are built, integrated and operated across the organisation
- Designing and maintainingstandardised templates and reference implementationsfor LLM and Generative AI workflows, enabling teams to adopt consistent patterns for prompt design, tool calling, multi‑step agent flows, retries and failure handling
- Implementingsecure, governed access patternsfor LLMs and enterprise tools usingAPIM, platform gateways,Entra ID,RBACandmanaged identities
- Contributing toLLMOps and model runtime patterns, including standard approaches for model access, routing, caching, token optimisation and cost‑aware usage controls
- Supportinglifecycle and evaluation practicesfor agent configurations, prompts and AI workflows, including testing, controlled change and release readiness
- Designingsecure tool-access patternsfor agents, including MCP/tool abstraction, credential management and enterprise API integration.
- Contributing toAgentOps and GenAIOps capabilities, including telemetry, run history, task outcomes, error analysis and feedback loops
- Contributing toreliability patternsfor production AI systems, including latency monitoring, alerting, scaling considerations and operational readiness.
- ApplyingCI/CD and software engineering best practicesto AI platform and agentic components
- Embeddingobservability by default, ensuring AI systems are measurable, debuggable and auditable through logs, metrics and traces
- Partnering with Cloud Infrastructure and Security teams to designsecure, scalable and cost‑effective Azure environments
Qualifications
- Significant experience as anAI Engineer, AI Platform Engineer or similar, deliveringproduction‑grade AI systems
- Hands‑on experience withLLMs, Generative AI and agent‑based systemsin real‑world environments
- Strong understanding of theend‑to‑end AI lifecycle, from experimentation through deployment and operation
- Practical understanding ofproduction LLM or GenAI runtime concerns, such as model access, routing, caching, token usage, cost optimisation and reliability.
- High proficiency inPython, with experience building APIs and service‑oriented systems
- Experience working withCI/CD pipelines, automated testing and versioned deployments for AI or platform components
- Practical experience withobservability tooling(logging, metrics, tracingand alerting) and using telemetry to improve reliability and performance
- Experience withAzure AI Foundry is preferred, but we are equally open to candidates with hands‑on experience usingcomparable GenAI or agent platforms, and a strong understanding of how to apply those patterns within Azure
- Experience withAzure API Management (APIM)is preferred, especially as a governance or integration boundary
- Familiarity withAgentOps, MLOps or GenAIOpsconcepts, including monitoring, evaluation and feedback loops
- Strong collaboration skills, with the ability to influence platform standards and enable other engineering teams
- A pragmatic, engineering‑led approach toresponsible and ethical AI, with a focus on safety, reliability and trust
Additional Information
- Employee sample sales
- 25 days paid annual leave + an extra celebration day for a special moment
- Discretionary bonus scheme
- Private medical care scheme
- Flexible benefits allowance - which you can choose to take as extra cash, or use towards other benefits
- Opportunity for personalised learning and in‑the‑moment experiences that enable you to thrive and excel in your role