Sundayy
ML Engineer, Performance
Get notified of more jobs like this · No spam, ever
How your CV stacks up
Upload your CV to see how well it fits this job role
?%
About The Company
Founded in 2017, Wayve is at the forefront of Embodied AI technology development. Our innovative AI software and foundation models empower vehicles to perceive, understand, and navigate complex environments, significantly enhancing the safety and usability of automated driving systems. Our mission is to create autonomous solutions that propel the world forward through intelligent, mapless, and hardware-agnostic AI products designed for automakers. We are committed to accelerating the transition from assisted to fully automated driving, making transportation safer and more efficient. At Wayve, we thrive in a fast-paced environment where complex challenges inspire us to develop groundbreaking solutions. We value diversity, foster an inclusive work culture, and believe that every contribution matters. Our team is dedicated to continuous learning and innovation, paving the way for a smarter, safer future in mobility.
About The Role
As a Staff ML Performance Engineer at Wayve, you will play a pivotal role in high-impact projects focused on optimizing machine learning inference for edge accelerators and GPUs. Your primary responsibility will be to ensure that large transformer-based models run efficiently on low-cost, low-power edge devices, enabling Wayve’s first commercial driving product. This hands-on position requires collaboration across ML systems, compilers, runtimes, kernels, and embedded deployment teams. You will help define the technical strategy for transforming these models into reliable, production-ready systems that operate seamlessly within in-vehicle compute environments. Your expertise will directly influence the performance, scalability, and robustness of our AI solutions, contributing to several early-stage initiatives that are critical to our company's growth and success.
Reasons to use Rodeo
Start with a chat, not a search bar
Grad scheme, placement, apprenticeship? Not sure what you want yet — that's fine. Your agent talks it through with you and turns "I have no idea" into a shortlist.
It searches the market for you
Every day your agent scans the market matching roles against what actually matters to you, not just keywords on a CV.
Only hits
No noise. No "maybe this fits." Just roles with a clear explanation of why they're right — and where to focus when applying.
Qualifications
- Proven experience in improving performance in production systems under constraints such as latency, memory, bandwidth, power, or cost.
- Strong proficiency with relevant stacks or toolchains such as TensorRT, CUDA, Qualcomm QNN, Triton, OpenCL, MLIR, or ONNX.
- Ability to operate effectively across multiple levels of abstraction, from high-level model behavior to low-level kernel and runtime execution.
- Solid software engineering fundamentals, including debugging, profiling, testing, and writing maintainable code.
- Excellent communication skills and a collaborative mindset, capable of aligning multiple stakeholders on performance trade-offs and priorities.
- Experience with performance benchmarking, regression testing, and cross-platform development.
- Familiarity with embedded or edge deployment of ML models and system-level constraints.
- Proficiency in Python and C++ programming languages.
- Experience working with NVIDIA and/or Qualcomm SoCs and associated performance tools is desirable.
- Prior experience mentoring team members or driving technical direction within a fast-paced environment is a plus.
Responsibilities
- Identify, implement, and validate optimizations in ML compilers, runtimes, and kernels, including operator fusion, scheduling, quantization-aware performance, and custom kernel development.
- Profile inference workflows to detect bottlenecks across the entire stack—model graph, compiler/runtime, kernel execution, and memory movement—and deliver measurable performance improvements.
- Develop robust benchmarking and regression testing frameworks to ensure consistency and reliability of performance gains across models, hardware devices, and software releases.
- Collaborate with cross-functional teams to develop and optimize solutions for multiple target platforms such as NVIDIA Orin/Thor and Qualcomm, ensuring high performance and maintainability.
- Work closely with model developers to influence architecture and training/deployment strategies that enhance on-device performance.
- Contribute to the development of technical roadmaps, tooling, and best practices to elevate performance engineering standards within the team.
- Stay updated with emerging technologies and incorporate innovative techniques to improve inference efficiency on edge devices.
- Support system-level integration and troubleshooting during deployment to ensure seamless operation in real-world environments.
Get help with your application
Your very own career expert that helps elevate your application to the next level.
Benefits
- Competitive salary and performance-based bonuses.
- Comprehensive health insurance plans including medical, dental, and vision coverage.
- Flexible working hours and remote work options.
- Opportunities for professional development and continuous learning.
- Collaborative and inclusive work environment fostering innovation and growth.
- Participation in cutting-edge projects shaping the future of autonomous mobility.
- Generous paid time off and holiday leave policies.
Equal Opportunity
Wayve is an equal opportunity employer committed to fostering a diverse and inclusive workplace. We welcome applicants from all backgrounds regardless of sex, race, religion, ethnicity, disability, age, sexual orientation, gender identity, veteran status, or any other protected characteristic. We are dedicated to creating a respectful environment where everyone can thrive and contribute to our mission of transforming mobility through innovative AI solutions. If you require any accommodations during the interview process, please let us know. We value diversity and are committed to ensuring an equitable hiring experience for all candidates.
“It took my CV and asked me questions relevant to understanding what kind of jobs to suggest for me. Suggestions were almost perfect. Jobs were exactly what I’ve been looking for.”
Jessica, London
Skills
Location