Software Engineer, ML Performance Optimization

Team: Software Systems

Location: Foster City, CA

Commitment: Full-time

Workplace Type: onsite

Salary:

Base Salary Range

There are three major components to compensation for this position: salary, Amazon Restricted Stock Units (RSUs), and Zoox Stock Appreciation Rights. A sign-on bonus may be offered as part of the compensation package. The listed range applies only to the base salary. Compensation will vary based on geographic location and level. Leveling, as well as positioning within a level, is determined by a range of factors, including, but not limited to, a candidate's relevant years of experience, domain knowledge, and interview performance. The salary range listed in this posting is representative of the range of levels Zoox is considering for this position.

Zoox also offers a comprehensive package of benefits, including paid time off (e.g. sick leave, vacation, bereavement), unpaid time off, Zoox Stock Appreciation Rights, Amazon RSUs, health insurance, long-term care insurance, long-term and short-term disability insurance, and life insurance.

In this role, you will:

• 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.

Qualifications

Note: You do not have to meet all the requirements below to be considered for this position:
•  4+ years of total experience, including 2+ years of working on large-scale model training or inference platforms.
• 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 for identifying model training and serving bottlenecks.
• Proficient in Python or C++.