Software Engineer, ML Performance Optimization (AI)

TL;DR

Software Engineer, ML Performance Optimization (AI): Designing and operating ML training and inference optimization techniques for VLM, VLA, and foundational models for robotaxis with an accent on GPU efficiency and distributed training. Focus on scaling large-scale model platforms, identifying bottlenecks using profiling tools, and ensuring efficient deployment in autonomous vehicles.

Location: On-site in Foster City, CA

Company

Zoox is developing autonomous robotaxis to provide a safe and efficient transportation service.

What you will do

• Design, implement, and operate cutting-edge ML Training and Inference performance optimization techniques.
• Scale VLM, VLA, and Foundational models for efficient deployment within robotaxis.
• Collaborate with cross-functional teams, including ML researchers, software engineers, and hardware engineers, to align on architectural decisions.

Requirements

• 4+ years of total professional experience.
• 2+ years of experience working on large-scale model training or inference platforms.
• Proficiency in Python or C++.
• Experience with PyTorch and leveraging GPUs for distributed model training.
• Experience with GPU-accelerated inference using TensorRT or similar frameworks.
• Experience using profiling tools such as NVIDIA Nsight or PyTorch Profiler to identify bottlenecks.

Culture & Benefits

• Comprehensive health, long-term care, and life insurance.
• Paid time off, including sick leave and vacation.
• Equity compensation via Amazon RSUs and Zoox Stock Appreciation Rights.
• Potential for a sign-on bonus.