Senior/Staff Software Engineer, ML Inference Optimization

The role

You will drive ML inference optimization for autonomous driving models so they run fast and efficiently on the robotaxi. You will lead design and operation of performance techniques and work with Autonomy teams at Zoox.

What you will do

• Develop and execute a strategic vision for the ML Inference Optimization team.
• Lead design, implementation and operation of ML training or inference performance optimization techniques.
• Scale VLM, VLA and Foundational models and deploy them efficiently in the robotaxi.
• Collaborate with ML researchers, software, data and hardware engineers to define requirements and architecture.
• Provide technical guidance and mentorship to engineers on the team.

Required qualifications

• Strong experience with training frameworks like PyTorch, using GPUs efficiently for distributed training.
• Experience with GPU-accelerated inference using TensorRT or similar frameworks.
• Experience with profiling tools such as NVIDIA Nsight or PyTorch Profiler.
• Proficient in Python and C++.
• Experience with model compression techniques.

Nice to have

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

Before you apply

• You do not have to meet all the listed qualifications to be considered.

About the company

Zoox is developing the first ground-up, fully autonomous vehicle fleet and the supporting ecosystem to bring it to market. It aims to provide next-generation mobility-as-a-service in urban environments.