Edge ML Performance Engineer — Fast Inference for Embedded

Wayve

Greater London

Hybride

GBP 80 000 - 120 000

Plein temps

Il y a 10 heures

Soyez parmi les premiers à postuler

Générateur de candidature

N’envoyez pas de CV générique — générez un CV et une lettre de motivation adaptés à ce poste précis.

Passez les filtres ATS

Avantages offerts par ce poste

Meaningful equity

Relocation support

Hybrid working

Learning budgets

Health and dental insurance

Parental leave

Résumé du poste

Wayve is building the leading AI platform for autonomous driving. This hands-on ML performance role focuses on optimizing inference across edge accelerators and GPUs, turning research models into reliable production systems for Wayve's driving product.

You will profile and optimize across models, compilers, runtimes and embedded targets (e.g., NVIDIA Orin/Thor, Qualcomm). Collaboration with model, platform and deployment teams is essential to balance latency, memory and power with real-world

Qualifications

Hands-on performance tuning in production ML systems.
Experience with edge GPUs and embedded deployment.
Strong debugging, profiling and testing skills.

Responsabilités

Profile inference performance across model graphs, compiler/runtime behaviour, kernel execution and memory movement.
Implement optimisations in compilers, runtimes and/or kernels, including fusion, scheduling, quantisation-aware performance and 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.