Location
London (Hybrid working model with in-person collaboration and remote flexibility)

Hours
Full Time

Salary
Negotiable

About the Role
At Wayve, we build the embodied intelligence that moves real vehicles safely and the ecosystem a billion machines will run on in the future. As a Senior ML Performance Engineer in our ML performance team, you will optimise inference for edge accelerators and GPUs, enabling large transformer-based models to 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 powering Wayve's autonomous driving product.

This is a hands-on role spanning ML systems, compilers, runtimes, kernels, and embedded deployment. Your day-to-day work will involve identifying bottlenecks, implementing performance improvements, and collaborating with model developers to make deployment-aware decisions early in the development cycle.

Your responsibilities will include profiling inference performance across model graphs, compiler/runtime behavior, kernel execution, and memory movement; implementing and validating optimisations such as fusion, scheduling, quantisation-aware performance, and custom kernels; building benchmarking and regression tests to track performance across models, devices, and software releases; optimising for edge targets including NVIDIA Orin/Thor and Qualcomm platforms; and contributing to team tooling, documentation, and technical discussions around ML performance.

Wayve is pioneering an end-to-end AI platform for autonomous driving that learns directly from real-world experience. Our mapless, hardware-agnostic AI platform integrates with global OEM partners to enable continuous software evolution and unlock advanced levels of automation. Joining Wayve means contributing to a transformative technology that will shape the future of mobility.

Experience
- Proven experience improving performance in production or production-adjacent systems with constraints such as latency, memory, bandwidth, power, thermal, or cost
- 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 writing maintainable code

About you
- Excellent communication skills and ability to collaborate across ML, systems, and deployment teams
- Passionate about autonomy and keen to learn and grow within a fast-evolving environment
- Experience deploying or benchmarking ML models on embedded or edge devices is a plus
- Familiarity with NVIDIA and/or Qualcomm SoCs and performance tooling is desirable
- Proficiency in Python and C++ is advantageous
- Experience supporting other engineers or contributing to technical direction within a small team is beneficial

Qualifications
- No specific formal qualifications required; a strong passion for autonomy, learning, and problem solving is highly valued