Software Engineer (ML Performance Optimization)

Join Zoox, a company on a mission to revolutionize transportation with autonomous robotaxis. As a Software Engineer focused on ML Performance Optimization, you will play a crucial role in enabling innovations in large-scale Foundation models and making autonomous driving seamless. You will work with cutting-edge techniques in distributed training, quantization, distillation, and pruning, collaborating closely with cross-functional teams. This position offers numerous growth opportunities as Zoox expands its robotaxi deployments and ventures into new ML domains.

• Design, implement, and operate cutting-edge ML Training OR Inference performance optimization techniques to scale our VLM, VLA, and Foundational models and deploy them efficiently in our robotaxi.
• Collaborate closely with cross-functional teams, including ML researchers, software engineers, data engineers, and hardware engineers, to define requirements and align on architectural decisions.
• Work with SOTA accelerators, cutting-edge techniques in distributed training, quantization, distillation, and pruning, among other things, working closely with all the Autonomy teams within Zoox.
• 4+ years of total experience, including 2+ years of working on large-scale model training or inference platforms
• Proficient in Python or C++
• Experience with training frameworks like PyTorch, leveraging GPUs efficiently for distributed model training
• Note: You do not have to meet all the requirements below to be considered for this position:
• Experience using profiling tools like NVIDIA's Nsight or PyTorch's Profiler for identifying model training and serving bottlenecks
• Experience with GPU-accelerated inference using TensorRT or similar frameworks