Senior/Staff Software Engineer, ML Performance Optimization

About the Role

Zoox is on a mission to reimagine transportation and build autonomous robotaxis that are safe, reliable, clean, and enjoyable for everyone. The ML Platform team plays a crucial role in enabling innovations in large-scale Foundation models, VLMs, and VLAs to make autonomous driving seamless.

You will drive ML Performance Optimization initiatives to make our ML models as fast and efficient as possible. This includes working with state-of-the-art accelerators, distributed training, quantization, distillation, and pruning. You’ll collaborate closely with Autonomy teams—Perception, Prediction, Planner, Simulation, and Collision Avoidance—to push the boundaries of ML at Zoox.

The team builds and operates the foundational layer of ML tools, model development, and serving systems for in- and off-vehicle use cases. You’ll work alongside strong software engineers and act as a force multiplier for internal customers, with growth opportunities as we expand robotaxi deployments and explore new ML domains.

Responsibilities

• Develop and execute a strategic vision for the ML Performance Optimization team to unlock ML innovation in autonomous driving and rider experience.
• Lead the design, implementation, and operation of cutting-edge ML training or inference performance optimization techniques to scale VLMs, VLAs, and Foundational models, deploying them efficiently in our robotaxi.
• Collaborate with cross-functional teams, including ML researchers, software engineers, data engineers, and hardware engineers, to define requirements and align on architectural decisions.
• Provide technical guidance and mentorship to engineers on the team to support their career growth.

Qualifications

Note: You do not need to meet all requirements to be considered.

• Strong experience with training frameworks like PyTorch, leveraging GPUs efficiently for distributed model training.
• Experience with GPU-accelerated inference using TensorRT or similar frameworks.
• Experience using profiling tools like NVIDIA's Nsight or PyTorch's Profiler to identify model training and serving bottlenecks.
• Proficiency in Python and C++.
• Experience with model compression techniques to reduce model size and improve performance.

Bonus Qualifications

• 10+ years of total experience, including 4+ years working on large-scale model training or inference platforms.
• Excellent leadership skills with a demonstrated ability to lead high-performing engineering teams.

Pay

$242,000 - $389,000 a year

About Zoox

Zoox is developing the first ground-up, fully autonomous vehicle fleet and the supporting ecosystem to bring this technology to market. Sitting at the intersection of robotics, machine learning, and design, Zoox aims to provide the next generation of mobility-as-a-service in urban environments.