Senior Edge ML Performance Engineer

Wayve; Greater London; Hybrid; GBP 110,000 - 180,000; Full time

Benefits offered by this job

Salary benchmarking

Equity participation

Relocation support

Hybrid work model

Learning budget and training

Job summary

Wayve is seeking a senior ML performance engineer to optimise inference for edge accelerators and GPUs within our driving platform. You will work closely with model, platform and deployment teams to translate research models into reliable production systems for our autonomous driving product.

You will directly influence bottlenecks, implement performance improvements, and drive decisions early in deployment.

Qualifications

• StrongHands-on experience with ML systems performance tuning and inference efficiency.

Responsibilities

• Profile inference performance across model graphs, compiler/runtime behaviour and memory movement.
• Implement optimisations in compilers/runtimes/kernels including fusion and quantisation-aware performance.
• Build benchmarking/regression tests to track performance across models, devices and software releases.
• Optimise for edge targets (e.g., NVIDIA Orin/Thor, Qualcomm platforms).
• Contribute to team tooling, documentation and technical discussions on ML performance.

Job description

Wayve is seeking a senior ML performance engineer to optimise inference for edge accelerators and GPUs within our driving platform. You will work closely with model, platform and deployment teams to translate research models into reliable production systems for our autonomous driving product.

You will directly influence bottlenecks, implement performance improvements, and drive decisions early in deployment.