Senior ML Performance Engineer, Inference Optimisation

Overview

In this role you optimise ML inference on edge hardware to enable efficient autonomous driving. You will work closely with model, platform and deployment teams to turn research models into reliable production systems for Wayve’s driving product. You’ll identify bottlenecks, implement performance improvements and guide deployment-aware decisions. The role offers hands-on work across ML systems and edge-targeted optimisations, with impact on safety and efficiency in real-world vehicles. You will contribute to tooling and documentation while collaborating across ML and systems teams.

Pay / Benefits

• market-competitive salary
• equity
• relocation support and visa sponsorship
• hybrid working with core hours
• learning and development budget
• comprehensive benefits (health insurance, dental, parental leave, pension, wellbeing resources)

Responsibilities

• Profile inference performance across model graphs, compiler/runtime behavior, kernel execution and memory movement
• Implement and validate optimisations in compilers, runtimes and/or kernels (fusion, scheduling, quantisation-aware performance, custom kernels)
• Build benchmarking and regression tests to track performance across models, devices and software releases
• Optimise for edge targets such as NVIDIA Orin/Thor and Qualcomm platforms
• Contribute to team tooling, documentation and technical discussions around ML performance

Key requirements

• Experience improving performance in production or production-adjacent systems under latency, memory, bandwidth, power, thermal or cost constraints
• Hands-on experience with TensorRT, CUDA, Qualcomm QNN, Triton or OpenCL
• Ability to work from high-level model behaviour down to kernel/runtime-level execution
• Strong software engineering fundamentals: debugging, profiling, testing and maintainable code
• Clear communication and ability to collaborate across ML, systems and deployment teams
• strong communication
• cross-functional collaboration
• problem-solving mindset
• TensorRT
• CUDA
• Qualcomm QNN

Report this job