ML Compression Engineer, Wayve

• 2+ years working as an MLE
• Experience working on optimisation problems with hard latency and/or resource constraints
• Strong engineering background
• Proficiency with PyTorch
• Excellent interpersonal and communication skills

Desirable

• As a Machine Learning Engineer for the ML Optimisation team, you’ll optimise our Driving Model to run efficiently in millions of vehicles with consumer-grade GPUs and accelerators
• The focus of this team is to run large transformer-based models efficiently in low-cost, low-power edge devices to enable Wayve’s first driving product - e.g. Via methods such as distillation, efficient architectures, pruning, quantisation and others
• This is an exciting opportunity to own and lead high impact, early stage projects at Wayve with the ultimate goal of enabling product deployments onto millions of customer vehicles around the world
• Develop state of the art techniques in distillation, quantisation, pruning and other ML compression methods to achieve latency, bandwidth and compute targets
• Understand how ML compression methods affect driving behaviour
• Stay up to date with latest papers, conferences etc
• You’ll collaborate closely with other model developers and scientists across the business to drive innovation and delivery
• You’ll have the opportunity to develop new skills and experience