Senior/Staff Software Engineer, ML Training Performance

Zoox; Foster City (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Zoox is seeking an experienced ML Platform engineer to own and optimize training performance for large-scale models. The role involves setting technical direction for distributed training, mixed-precision strategies, and RL on SOTA accelerators, with collaboration across Autonomy teams and internal customers.

The role requires leading projects end-to-end, driving multi-quarter roadmaps, and mentoring engineers to raise the team’s technical bar as we expand into new ML domains.

Qualifications

• 7+ years of total experience, incl. 4+ years on large-scale model training platforms.
• Experience with distributed training frameworks (Megatron-LM, TorchTitan) on GPU clusters.
• Proficiency in Python or C++ and strong profiling skills.

Responsibilities

• Lead the design, implementation, and operation of training performance optimizations to scale VLM, VLA, and Foundation model training.
• Own the technical strategy and multi-quarter roadmap for RL framework and RL performance optimization for driving foundation models.
• Drive profiling and root-cause analysis of throughput bottlenecks across compute, compiler, framework, and cluster-networking stack.
• Partner with ML researchers, data engineers, and hardware engineers to define requirements and make architectural decisions for large-scale training infrastructure.
• Build custom kernels and benchmarks that track and validate performance gains across the stack.
• Mentor engineers and raise the team’s technical bar through design reviews and best practices.

Skills

Python

C++

Distributed training

Profiling tools

Leadership

Cross-team communication

Tools

Megatron-LM

TorchTitan

NCCL

Job description

Zoox is on a mission to reimagine transportation and build ground-up autonomous robotaxis that are safe, reliable, clean, and enjoyable for everyone. We’re still early in deploying on public roads, so this is a great time to join and have a significant impact. The ML Platform team enables innovation in large-scale Foundation models, VLMs, and VLAs to make autonomous driving as seamless as possible.

The Opportunity

Are you excited to own ML training performance at Zoox and make the models that power autonomous driving train faster, cheaper, and at greater scale? You’ll set technical direction for distributed training, parallelism strategies, mixed-precision training, and RL on SOTA accelerators, especially for multi-modal VLA and VLM models. You’ll partner with all Autonomy teams (Perception, Prediction, Planner, Simulation, Collision Avoidance) and act as a force multiplier for our internal customers, while mentoring engineers and shaping the team’s roadmap as we expand into new ML domains. If you want to learn more about our stack behind autonomous driving, please look here. If you want to learn more about our ML Infrastructure, here is one of our past talks at re:Invent.

In this role, you will:

• Lead the design, implementation, and operation of training performance optimizations (data/tensor/pipeline parallelism, mixed precision, gradient checkpointing, GPU kernels) to scale VLM, VLA, and Foundation model training.
• Own the technical strategy and multi-quarter roadmap for RL framework and RL performance optimization for driving foundation models.
• Drive profiling and root-cause analysis of throughput bottlenecks across the compute, compiler, framework, and cluster-networking stack.
• Partner with ML researchers, data engineers, and hardware engineers to define requirements and make architectural decisions for large-scale training infrastructure.
• Build custom kernels and benchmarks that track and validate performance gains across the stack.
• Mentor engineers and raise the team’s technical bar through design reviews and best practices.

Qualifications

Note: You do not have to meet all the requirements below to be considered for this position:

• 7+ years of total experience, including 4+ years on large-scale model training platforms, with a record of leading projects end to end.
• Deep experience with distributed training frameworks (Megatron-LM, TorchTitan) and efficiently utilizing GPU/accelerator clusters at scale.
• Experience with RL frameworks (Verl/MILES) and algorithms (GRPO, PPO).
• Experience with collective communication libraries (e.g., NCCL) and optimizing communication/compute overlap in multi-node training.
• Strong command of profiling tools (NVIDIA Nsight, PyTorch Profiler, or XLA/JAX profiling) to find and resolve training bottlenecks.
• Proficiency in Python or C++.
• Experience with ML compilers, performance tooling, or hardware/software co-design (GPU/TPU/accelerator architectures).
• Ability to influence across teams and communicate technical tradeoffs to both researchers and engineers.