Staff Ml Performance Engineer (inference Optimisation)

Staff ML Performance Engineer at Wayve focused on optimizing ML inference for edge accelerators and GPUs. The role involves running large transformer-based models efficiently on low-power edge devices, setting technical direction for production systems, and hands-on work across ML systems, compilers, runtimes, kernels, and embedded deployment.

Skills and focus areas

• ml performance engineering
• inference optimization
• edge computing
• gpu optimization
• transformer models
• compiler optimization
• runtime optimization
• kernel development
• embedded systems
• performance profiling
• benchmarking
• regression testing