Staff Machine Learning Performance Engineer, Inference Optimisation

A Staff/Principal ML Performance Engineer leading high-impact projects to optimise ML inference for edge accelerators and GPUs, enabling Wayve’s first driving product. The role focuses on running large transformer-based models efficiently on low-cost, low-power edge devices and operates at the intersection of ML compilers, kernels, and ML engineering. It involves building technical roadmaps, collaborating across teams, and contributing to early-stage product development.