Senior AI Engineer (AI Platform)

Overview

As a Senior AI Engineer, you will help build and scale ASOS’s AI Platform, focusing on agentic AI capabilities on Azure. You will shape shared standards, templates, and reference implementations to enable enterprise-scale AI agent design, deployment, and operation. You’ll collaborate across Product, Cloud Infra, and Security to ensure secure, observable, and governed AI foundations, while advancing LLMOps and reliable production readiness. This is a platform-focused role with a strong impact on how teams build and use AI at scale.

Pay / Benefits

• employee discount (ASOS)
• employee sample sales
• 25 days paid annual leave + 1 extra celebration day
• discretionary bonus scheme
• private medical care
• flexible benefits allowance

Responsibilities

• Design and implement AI platform capabilities on Azure with agent runtimes, orchestration, and tool integration
• Contribute to the Agentic AI Platform initiative, defining how agents are built, integrated and operated across the organisation
• Create standardised templates and reference implementations for LLM/GenAI workflows (prompt design, tool calling, multi-step flows, retries, failure handling)
• Implement secure, governed access patterns for LLMs and enterprise tools using APIM, gateways, Entra ID, RBAC, and managed identities
• Contribute to LLMOps and model runtime patterns (model access, routing, caching, token optimization, cost-aware usage)
• Support lifecycle and evaluation practices for agent configurations, prompts and AI workflows (testing, change control, release readiness)
• Design secure tool-access patterns for agents (MCP/tool abstraction, credential management, enterprise API integration)
• Contribute to AgentOps/GenAIOps capabilities (telemetry, run history, task outcomes, error analysis, feedback loops)
• Contribute to reliability patterns for production AI systems (latency monitoring, alerting, scalability, operational readiness)
• Apply CI/CD and software engineering best practices to AI platform components
• Embed observability by default (logs, metrics, traces) to enable measurability, debuggability and auditable systems
• Partner with Cloud Infra and Security to design secure, scalable Azure environments

Key requirements

• Significant experience as AI Engineer/AI Platform Engineer delivering production-grade AI systems
• Hands-on experience with LLMs, Generative AI, and agent-based systems in real-world environments
• Strong understanding of end-to-end AI lifecycle from experimentation to deployment and operation
• Production LLM/GenAI runtime concerns (model access, routing, caching, token usage, cost optimization, reliability)
• High proficiency in Python with API and service-oriented development
• Experience with CI/CD pipelines, automated testing, and versioned deployments for AI/platform components
• Observability tooling experience (logging, metrics, tracing, alerting) and using telemetry to improve reliability
• Cloud experience, preferably Azure; familiarity with Azure Foundry or comparable GenAI/agent platforms
• Experience with Azure API Management (APIM) is preferred
• Familiarity with AgentOps, MLOps or GenAIOps concepts (monitoring, evaluation, feedback loops)
• Strong collaboration and ability to influence platform standards
• Pragmatic, engineering-led approach to responsible and ethical AI focusing on safety, reliability, and trust

• Collaborative mindset
• Influence across teams
• Problem solving with a practical, engineering-led approach
• LLMs and Generative AI
• Agent-based systems
• Python API and service-oriented architecture

…