Senior / Staff ML Onboard Optimization Engineer

You will...

• Collaborate closely with autonomy and algorithm engineers to scale safe self-driving systems using an AI-first approach.
• Expand the model deployment pipeline to new GPUs and embedded systems for the next generation of our onboard compute system.
• Use frameworks such as TensorRT and modelopt to optimize the models running on the truck.
• Create and benchmark new CUDA kernels for inference.
• Comprehensively profile model runtime and memory to pinpoint performance bottlenecks.

Qualifications:

• MS/PhD or Bachelors degree with a minimum of 6 years of industry experience in Computer Science, Robotics and/or similar technical field(s) of study.
• Solid coding proficiency in a variety of coding languages including Python, C++ or Rust.
• Experience in deep learning frameworks such as PyTorch.
• Skilled in profiling CPU and GPU code using tools such as PyTorch Profiler and NVIDIA Nsight.
• Experience with Nvidia embedded platforms such as Nvidia Jetson or Thor.
• Open-minded and collaborative team player with willingness to help others.
• Passionate about self-driving technologies, solving hard problems, and creating innovative solutions.

Bonus/nice to have:

• Experience in model compilation and exporting, interaction with lower level concepts like TensorRT.
• Experience in identifying when custom CUDA kernels are needed, and implementing them.
• Experience in Bazel build systems, and integrating third party packages into dev environments.