Senior Machine Learning Scientist (Personalisation)

Overview

In this Senior Machine Learning Engineer role, you will design, build and run ML systems at ASOS to help customers discover outfits that reflect their personal style and current trends. You’ll work within a cross-functional Personalisation team to productionise ML at scale, partnering with engineers, data scientists and product teams. You will help drive high-impact improvements to the customer experience through thoughtful ML solutions. This position offers an opportunity to shape recommendation and targeting capabilities in a fast-paced, fashion-focused environment.

Pay / Benefits

• Employee discount (ASOS)
• Employee sample sales
• 25 days paid annual leave + 1 extra celebration day
• Discretionary bonus scheme
• Private medical care scheme
• Flexible benefits allowance

Responsibilities

• Build and improve algorithms used for pricing and customer targeting
• Collaborate with scientists and engineers to deploy ML solutions at scale for hundreds of millions of products and customers
• Deploy and maintain batch and real-time ML models in production
• Evolve codebase, tooling and platforms; contribute to new feature design
• Mentor and support junior engineers to grow technical skills
• Contribute to ML technical direction and share knowledge across ASOS ML and engineering communities

Key requirements

• Production experience applying machine learning in real-world environments with emphasis on deep learning
• Experience with recommendation or ranking systems (or strong interest)
• Familiarity with modern deep learning frameworks and distributed training for large-scale models
• Experience training models across GPUs with data/model parallelism or willingness to deepen knowledge
• Solid software engineering basics: data pipelines, CI/CD, containerisation, observability; exposure to MLOps tooling
• Comfortable providing technical guidance and mentoring to less-experienced engineers
• Ability to collaborate across teams and contribute to shared engineering initiatives

• collaboration across teams
• mentoring and coaching
• communication of technical concepts to non-technical stakeholders
• deep learning
• recommendation/ranking systems
• GPU-based training and data/model parallelism

…