ML Performance Engineer

About The Company Founded in 2017, Wayve is a pioneering leader in Embodied AI technology, dedicated to transforming autonomous driving systems. Our innovative AI software and foundational models empower vehicles to perceive, understand, and navigate complex environments with high precision and safety. By leveraging cutting-edge advancements in artificial intelligence, Wayve aims to accelerate the transition from assisted to fully automated driving, creating safer and more efficient transportation solutions worldwide. Our vision is to develop autonomous systems that propel the world forward through intelligent, mapless, and hardware-agnostic AI products. We foster a fast-paced, challenging environment where complex problems inspire innovative solutions. At Wayve, we value diversity, encourage new perspectives, and promote an inclusive workplace culture. We believe that every contribution matters and that collaborative effort drives our success. Join us to be part of a team that is shaping the future of mobility and making a meaningful impact on society. About The Role As a Staff Machine Learning Performance Engineer at Wayve, you will play a critical role in optimizing inference performance for edge accelerators and GPUs, directly impacting the development of our first autonomous driving product. Your expertise will be instrumental in ensuring that large transformer-based models operate efficiently on low-cost, low-power edge devices, enabling real-time processing and reliable vehicle operation. This role involves setting the technical direction for deploying these models into production environments, ensuring their robustness and efficiency on in-vehicle compute platforms. You will work hands-on across various aspects of ML systems, including compilers, runtimes, kernels, and embedded deployment, contributing to innovative projects at an early stage. Your work will help enhance the performance, scalability, and maintainability of our AI solutions, ultimately advancing Wayve’s mission to create smarter, safer autonomous systems. Qualifications Proven experience improving performance in production ML systems with constraints such as latency, memory, bandwidth, power, or costStrong proficiency with ML toolchains and frameworks such as TensorRT, CUDA, Qualcomm QNN, Triton, OpenCL, MLIR, or ONNXExperience operating across multiple levels of abstraction, from high-level model behavior to low-level kernel and runtime executionSolid software engineering fundamentals, including debugging, profiling, testing, and writing maintainable codeExcellent communication skills and ability to collaborate effectively with cross-functional teamsExperience with embedded or edge deployment of ML models and benchmarking on real devicesProficiency in Python and C++ is preferredExperience with NVIDIA and/or Qualcomm SoCs and performance tooling is desirableExperience mentoring team members and influencing technical decisions 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 developmentProfile inference stacks to pinpoint bottlenecks across model graphs, compiler/runtime layers, kernel execution, and memory movement, delivering measurable improvementsDevelop and maintain benchmarking and regression testing frameworks to ensure consistent performance gains across models, devices, and software releasesCollaborate with cross-functional teams to develop optimized solutions for multiple target platforms such as NVIDIA Orin/Thor and QualcommWork closely with model developers to influence architecture and training/deployment decisions that impact on-device performanceContribute to the development of technical roadmaps, tooling, and best practices to elevate the team’s performance engineering standardsStay updated with emerging technologies and industry trends to continuously improve inference performance and deployment strategies Benefits Competitive salary and performance-based incentivesComprehensive health insurance plansFlexible working hours and remote work opportunitiesProfessional development programs and continuous learning supportInclusive and diverse work environmentOpportunities to work on cutting-edge autonomous driving technologiesCollaborative and innovative company culture Equal Opportunity Wayve is committed to fostering an inclusive, diverse, and equitable work environment. We provide equal employment opportunities to all employees and applicants without regard to race, ethnicity, gender, sexual orientation, age, disability, religion, or any other protected status. We believe that diverse perspectives drive innovation and excellence, and we are dedicated to ensuring a fair and respectful workplace for everyone. If you require accommodations during the interview process, please let us know. We value your unique skills and contributions and are committed to supporting your success at Wayve.