The role
As a Staff ML Performance Engineer, you’ll play a key role in high-impact projects, optimising ML inference for edge accelerators and GPUs. The focus of this team is to run large transformer-based models efficiently on low-cost, low-power edge devices to enable Wayve’s first driving product.
You’ll help set the technical direction for turning these models into production systems that run reliably on in-vehicle compute. This is a hands-on role working across ML systems, compilers, runtimes, kernels, and embedded deployment, contributing to several early-stage, high-impact projects at Wayve.
Key responsibilities:
- Identify, implement and validate optimisations in ML compilers, runtimes, and kernels (e.g. operator fusion, scheduling, quantisation-aware performance, custom kernels)
- Profile and pinpoint bottlenecks across the full inference stack (model graph, compiler/runtime, kernel execution, memory movement) and deliver measurable improvements.
- Build robust benchmarking and regression testing to ensure performance improvements hold across models, devices, and software releases.
- Develop and optimise for multiple target platforms (e.g. NVIDIA Orin/Thor, Qualcomm), working with cross-functional teams to deliver performant and maintainable solutions.
- Collaborate with model developers to influence architecture and training/deployment decisions that affect on-device performance.
- Contribute to technical roadmaps and tooling and help raise the standard of performance engineering across the team
About you
Essential
- Proven experience improving performance in production systems with tight constraints (latency, memory, bandwidth, power/thermal, or cost).
- Strong proficiency with at least one relevant stack/toolchain (e.g. TensorRT, CUDA, Qualcomm QNN, Triton, OpenCL, MLIR, ONNX) and confidence learning adjacent frameworks quickly.
- Comfort operating at multiple levels of abstraction — from high-level model behaviour down to low-level kernel/runtime execution.
- Strong software engineering fundamentals (debugging, profiling, testing, and maintainable code).
- Clear communicator and collaborative teammate; able to align multiple stakeholders on performance trade-offs and priorities.
Desirable
- Experience with compute graph scheduling and execution on multiple targets
- Exposure to embedded or edge deployment of ML models, including benchmarking on real devices and handling system-level constraints.
- Experience with NVIDIA and/or Qualcomm SoCs and performance tooling.
- Python and C++ proficiency.
- Experience mentoring others and/or driving technical direction in a small, fast-moving team.
#LI-HH1