Senior/Staff Software Engineer, ML Training Performance (AI)

Location: On-site in Foster City, California or Seattle, Washington, United States

Company

Zoox develops autonomous robotaxis designed to provide safe, reliable, clean, and enjoyable transportation.

What you will do

• Lead training performance optimizations using data, tensor, and pipeline parallelism, mixed precision, gradient checkpointing, and GPU kernels.
• Own the technical strategy and multi-quarter roadmap for reinforcement learning frameworks and performance optimization for driving foundation models.
• Profile the compute, compiler, framework, and cluster-networking stack to identify and resolve throughput bottlenecks.
• Partner with ML researchers, data engineers, and hardware engineers on requirements and architecture for large-scale training infrastructure.
• Build custom kernels and benchmarks to validate performance improvements.
• Mentor engineers and improve technical practices through design reviews and engineering standards.

Requirements

• 7+ years of total experience, including 4+ years working on large-scale model training platforms and leading projects end to end.
• Deep experience with distributed training frameworks such as Megatron-LM and TorchTitan, and with GPU or accelerator clusters at scale.
• Experience with reinforcement learning frameworks such as Verl or MILES and algorithms including GRPO and PPO.
• Experience with collective communication libraries such as NCCL and optimizing communication and compute overlap in multi-node training.
• Strong command of NVIDIA Nsight, PyTorch Profiler, or XLA/JAX profiling tools, plus proficiency in Python or C++.
• Experience with ML compilers, performance tooling, hardware/software co-design, or GPU, TPU, and accelerator architectures; ability to communicate technical trade-offs across teams.

Culture & Benefits

• Work with autonomy, perception, prediction, planning, simulation, and collision-avoidance teams.
• Contribute to large-scale foundation models, VLMs, and VLAs for autonomous driving.
• Shape the ML training infrastructure roadmap as the organization expands into new ML domains.
• Help build a diverse engineering organization with varied backgrounds, experiences, and skills.