Machine Learning Engineer, Inference Optimisation

As a Machine Learning Engineer on the ML Optimisation team, you will optimize the Driving Model to run efficiently in millions of vehicles on consumer-grade GPUs and edge accelerators. You will develop state-of-the-art techniques in distillation, quantisation, pruning and other ML compression methods to reduce latency, bandwidth and compute requirements, while ensuring driving performance remains robust. You will evaluate how compression methods affect driving behavior, stay up to date with the latest literature, and collaborate closely with model developers and scientists to drive innovation and delivery. You will have opportunities to develop new skills and contribute to early-stage projects with the goal of product deployments at scale.