Staff Machine Learning Engineer, Inference Optimisation

As a Staff/Principal MLE in the ML Optimisation team, you will optimize the driving model to run efficiently on consumer GPUs and edge accelerators in millions of vehicles. You’ll develop and apply advanced model compression techniques such as distillation, quantisation, pruning, and sparsity to meet latency, bandwidth and compute targets. Assess how compression methods impact driving behaviour and safety requirements. Stay up to date with the latest research and papers, and translate insights into practical solutions. Collaborate closely with other model developers and scientists to drive innovation and deliver impactful results. Lead high-impact, early-stage projects with opportunities to deploy products at scale in consumer vehicles.