Senior ML Performance Engineer, Inference Optimisation
Salary not listed • London, United Kingdom • Full-time
Posted 28d ago
About the job
Wayve is building the leading AI platform for autonomous driving, pioneering an end-to-end AI approach that enables vehicles to learn directly from real-world experience. This role is within the ML performance team, which optimizes inference for edge accelerators and GPUs, ensuring large transformer-based models run efficiently on low-cost, low-power in-vehicle compute. You will work closely with model, platform, and deployment teams to transform research models into reliable production systems for Wayve's driving product. This is a hands-on position involving ML systems, compilers, runtimes, kernels, and embedded deployment, focusing on identifying bottlenecks, implementing performance improvements, and collaborating with model developers on performance trade-offs.
Responsibilities
- Profile inference performance across model graphs, compiler/runtime behavior, kernel execution, and memory movement.
- Implement and validate optimizations in compilers, runtimes, and/or kernels, including fusion, scheduling, quantization-aware performance, and custom kernels.
- Build benchmarking and regression tests to track performance across models, devices, and software releases.
- Optimize for edge targets such as NVIDIA Orin/Thor and Qualcomm platforms.
- Contribute to team tooling, documentation, and technical discussions around ML performance.
Requirements
- Experience improving performance in production or production-adjacent systems with latency, memory, bandwidth, power, thermal, or cost constraints.
- Strong hands-on experience with at least one relevant stack, such as TensorRT, CUDA, Qualcomm QNN, Triton, or OpenCL.
- Comfortable working from high-level model behavior down to kernel/runtime-level execution.
- Strong software engineering fundamentals, including debugging, profiling, testing, and maintainable code.
- Clear communication and ability to work well across ML, systems, and deployment teams.
- Python and C++ proficiency (nice to have).
- Experience deploying or benchmarking ML models on embedded or edge devices (nice to have).
- Familiarity with NVIDIA and/or Qualcomm SoCs and performance tooling (nice to have).
Benefits
- Salaries benchmarked against the market annually
- Meaningful equity
- Relocation support
- Visa sponsorship
- Hybrid working
- Core hours
- Chance to work hands-on in vehicle workshops and labs
- Learning and development budgets
- Support for training, conferences, and growth
- Comprehensive benefits including health insurance, dental, enhanced maternity and paternity leave, retirement or pension, access to therapists, wellbeing partnerships, team socials