jobs

Staff ML Performance Engineer (Inference Optimisation)

About us Founded in 2017, Wayve is the leading developer of Embodied AI technology. Our advanced AI software and foundation models enable vehicles to perceive, understand, and navigate any complex environment, enhancing the usability and sa

In inglese

Company

Wayve

Location

London

Status

Open

Posted

2026-05-14T10:20:07+00:00

Wayve is hiring a Staff ML Performance Engineer in London to make large transformer models run efficiently on low-cost, low-power in-vehicle accelerators and GPUs. The work covers profiling the full inference stack, writing compiler, runtime and kernel optimisations (operator fusion, scheduling, quantisation-aware performance), building benchmarking and regression tests, and targeting NVIDIA Orin/Thor and Qualcomm hardware. The posting wants production performance experience under tight latency, memory and power constraints, plus fluency in one of TensorRT, CUDA, Qualcomm QNN, Triton or OpenCL.