Senior Edge ML Performance Engineer

Icehouseventures; Greater London; On-site; GBP 90,000 - 130,000; Full time

Job summary

Wayve in London is seeking a Staff ML Performance Engineer to optimize inference for edge accelerators and GPUs, enabling transformer models to run efficiently on low-power devices for Wayve's driving product.

You will steer technical direction for production systems, work across ML systems, compilers, runtimes, and embedded deployment on multiple targets, collaborating with model developers to influence architecture and deployment decisions.

Qualifications

• Proven experience improving performance in production systems.
• Strong proficiency with stack/toolchain such as TensorRT, CUDA, Qualcomm QNN, Triton, OpenCL, MLIR or ONNX.
• Comfort operating across abstraction levels from high-level model behavior to low-level kernel/runtime execution.
• Strong software engineering fundamentals (debugging, profiling, testing, maintainable code).
• Clear communicator and collaborative teammate; able to align stakeholders on trade-offs.

Responsibilities

• Identify, implement and validate optimisations in ML compilers, runtimes, and kernels (e.g., operator fusion, scheduling, quantisation‑aware performance).
• Profile and pinpoint bottlenecks across the inference stack and deliver measurable improvements.
• Build robust benchmarking and regression tests to ensure improvements hold across models and devices.
• Develop and optimise for multiple target platforms (e.g., NVIDIA Orin/Thor, Qualcomm).
• Collaborate with model developers to influence architecture and deployment decisions for on‑device performance.
• Contribute to roadmaps and tooling to raise performance standards across the team.

Skills

Latency optimization

Profiling

Communication

Collaborative teamwork

Software engineering fundamentals

Tools

TensorRT

CUDA

Qualcomm QNN

Triton

OpenCL

MLIR

ONNX

Job description

Wayve in London is seeking a Staff ML Performance Engineer to optimize inference for edge accelerators and GPUs, enabling transformer models to run efficiently on low-power devices for Wayve's driving product.

You will steer technical direction for production systems, work across ML systems, compilers, runtimes, and embedded deployment on multiple targets, collaborating with model developers to influence architecture and deployment decisions.