Senior AI / LLM Engineer

asos.com Ltd
London, UK
2 days ago
Apply on jobs.smartrecruiters.com
Prepare application

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Working hours
Regular working hours

Tech stack

Application Programming Interfaces (APIs) Artificial Intelligence Microsoft Azure Cloud Computing Continuous Integration Python (Programming Language) Azure Machine Learning Software Safety Search Technologies Tokenization Workflow Management Systems Large Language Models
+6 more
Multi-Agent Systems Event Driven Architecture Build Management AI Platforms Machine Learning Operations GPT

Job description

We’re hiring a Senior AI / LLM Engineer to design and industrialise the core AI capabilities that will power ASOS.

At ASOS, AI is central to how we evolve the customer experience - from product discovery and personalisation through to operational decision-making. You’ll work on systems that operate at real scale, supporting experiences used by millions.

This role sits at the centre of our AI differentiation - focused on solving deep technical problems (models, reasoning systems, orchestration), not just feature delivery. You’ll create reusable, production-grade AI platforms that teams across ASOS can leverage, accelerating how we build and scale intelligent products.

We’re looking for someone who thinks in systems, not features - with strong abstraction capability and a mindset of building once and reusing at scale. You’ll be comfortable operating in ambiguity, working on frontier AI problems, and balancing innovation with the realities of production environments.

If you’re motivated by solving complex challenges and seeing your work adopted across a global platform, this is a high-impact opportunity.

Responsibilities

  • Design and build LLM-powered systems (RAG, fine-tuning, tool use, multi-agent orchestration)
  • Develop agentic workflows for automation, reasoning, and conversational experiences
  • Define patterns for autonomous + human-in-the-loop systems
  • Build and scale solutions on the Azure AI stack (Azure OpenAI, AI Studio, Azure ML, Cognitive Services)
  • Create reusable infrastructure: Prompt orchestration layers, Vector search and retrieval pipelines & Evaluation and observability frameworks
  • Design and implement LLM evaluation frameworks (offline + online)
  • Implement AI safety guardrails (hallucination control, filtering, explainability)
  • Partner with Trust & Security to embed AI risk controls by design
  • Build reusable AI capabilities (e.g. stylist reasoning, product understanding, copilots)
  • Enable horizontal reuse across squads - building once, scaling many times
  • Optimise systems for performance, cost, and reliability (token-aware design)
  • Champion best practice in AI engineering, governance, and platform thinking
  • Support a culture of inclusive, responsible AI development

Requirements

Tech stack & platform experience (core):

  • Strong hands-on experience with the Azure AI ecosystem - including Azure OpenAI, Azure AI Studio, and Azure Machine Learning
  • Experience building and running production-grade AI systems on cloud infrastructure (APIs, event-driven architectures, scalable compute such as AKS or similar)
  • Proficiency in Python, with experience working across modern AI frameworks (e.g. Semantic Kernel, LangChain or equivalents)

LLM systems and architecture:

  • Deep understanding of LLMs and transformer-based models, including embeddings, tokenisation, and context management
  • Experience designing and optimising LLM-powered systems, including fine-tuning approaches, structured prompting, and model selection trade-offs
  • Experience building end-to-end RAG pipelines, including retrieval strategies, vector search, and grounding techniques

Agentic systems & orchestration:

  • Experience designing agent-based systems, including multi-agent patterns, tool usage, and workflow orchestration
  • Understanding of state, memory, and event-driven pipelines in conversational or decisioning systems

Quality, safety & production readiness:

  • Experience implementing evaluation frameworks to measure model quality and performance
  • Strong understanding of AI safety, governance, and guardrails (hallucination mitigation, content safety, explainability)
  • Experience designing secure, scalable, and cost-efficient systems in production environments

Nice to have:

  • LLMOps / MLOps experience (CI/CD, experiment tracking, observability)
  • Performance and cost optimisation (caching, batching, model routing)

Benefits & conditions

BeneFITS’

  • Employee discount (hello ASOS discount!)
  • 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

About the company

We’re ASOS, 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’re free 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’re Disability Confident Committed - let our Talent team know if you need any reasonable adjustments throughout the recruitment process

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on jobs.smartrecruiters.com
Prepare application

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

40 sec

Generative pre-trained transformer models powering code completions

lgonta lgonta +1 · World Congress 2024

2:36 min

Choosing between managed AI platforms and custom governance

Péter Farkas Péter Farkas · Europe 2026 Virtual

3:12 min

Anatomy of misleading metrics and token leaderboards

Laura Tacho Laura Tacho · World Congress 2026 Europe

4:57 min

Centralizing LLMOps workflows within Azure AI Foundry

Maxim Salnikov Maxim Salnikov · LIVE

3:03 min

Career evolution in data engineering and AI platforms

Maria Apazoglou · Coffee With Developers

51 sec

Assessing GPT-4o performance for pull request feedback

Merrill Lutsky Merrill Lutsky · World Congress 2025

Videos

See all

Related articles

See all