Staff ML Performance Engineer

About the Company

Founded in 2017, Wayve is the leading developer of Embodied AI technology. Our advanced AI software and foundation models enable vehicles to perceive, understand, and navigate any complex environment, enhancing the usability and safety of automated driving systems.

Responsibilities

• Profile and pinpoint bottlenecks across the full inference stack including model graph, compiler, runtime, kernel execution, and memory movement
• Implement and validate optimisations in compilers, runtimes, and kernels such as operator fusion, scheduling, and quantisation-aware performance
• Build robust benchmarking and regression testing to ensure performance improvements hold across models and devices
• Optimise for multiple targets including NVIDIA Orin/Thor and Qualcomm
• Collaborate with model developers to influence architecture and deployment decisions
• Contribute to technical roadmaps and tooling to raise performance engineering standards

Requirements

• Proven experience improving performance in production systems with tight constraints (latency, memory, bandwidth, power, or cost)
• Strong proficiency with at least one relevant stack or toolchain such as TensorRT, CUDA, Qualcomm QNN, Triton, or OpenCL
• Ability to operate at multiple levels of abstraction from high-level model behaviour to low-level kernel execution
• Strong software engineering fundamentals including debugging, profiling, and testing
• Clear communication and collaborative skills

Preferred Qualifications

• Exposure to embedded or edge deployment of ML models
• Experience with NVIDIA and/or Qualcomm SoCs and performance tooling
• Proficiency in Python and C++
• Experience mentoring others or driving technical direction in fast-moving teams