Staff ML Performance Engineer (Inference Optimization)

Salary: £60,000 - 60,000 per year

Requirements:

• Proven experience improving performance in production systems with tight constraints such as 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, and confidence learning adjacent frameworks quickly.
• Ability to operate at multiple levels of abstraction, from high-level model behaviour down to low-level kernel and runtime execution.
• Strong software engineering fundamentals, including debugging, profiling, testing and maintainable code.
• Clear communication skills and a collaborative approach, with the ability to align multiple stakeholders on performance trade-offs and priorities.
• Experience with 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.
• Proficiency in Python and C++.
• Experience mentoring others and/or driving technical direction in a small, fast-moving team.

Responsibilities:

• Profile and identify bottlenecks across the full inference stack, including the model graph, compiler or runtime, kernel execution and memory movement, and deliver measurable improvements.
• Implement and validate optimisations in compilers, runtimes and/or kernels, such as operator fusion, scheduling, quantisation-aware performance and custom kernels.
• Build robust benchmarking and regression testing to ensure performance improvements hold across models, devices and software releases.
• Optimise for multiple targets such as NVIDIA Orin, Thor and Qualcomm, and work with teams to support these in a maintainable way.
• Collaborate with model developers to influence architecture and training or deployment decisions that affect on-device performance.
• Contribute to technical roadmaps and tooling, and help raise the standard of performance engineering across the team.

Technologies:

• AI
• CUDA
• Embedded
• Hardware
• Support
• Python

More:

We are Wayve, founded in 2017 and a leading developer of Embodied AI technology. Our advanced AI software and foundation models help vehicles perceive, understand and navigate complex environments, improving the usability and safety of automated driving systems. Our vision is to create autonomy that propels the world forward, and our intelligent, mapless, hardware-agnostic products are designed for automakers to accelerate the shift from assisted to automated driving. We work in a fast-paced, high-impact environment where we embrace uncertainty, take on complex challenges and keep learning as we build a smarter, safer future. We value diversity, new perspectives and an inclusive culture where everyones contributions matter. This is a full-time role based in our London office, with a hybrid working policy that combines time together in our offices and workshops with time working from home.

last updated 34 week of 2026