Zoox
Senior/Staff Software Engineer, ML Inference Optimization
$254K–$350K
Foster City, CA +1 · On-site · Staff · Full-time · Posted Oct 28, 2023
- Location
- Foster City, CA
Seattle, WA - Experience
- No minimum years specified as a requirement; bonus qualification: 10+ years total, including 4+ years on large-scale model training or inference platforms.
About the job
Leads ML inference optimization to improve the performance and efficiency of models deployed in Zoox robotaxis.
What you'll do
- Set the strategic vision for the ML Inference Optimization team.
- Lead design, implementation, and operation of training or inference performance optimization for VLM, VLA, and foundation models.
- Collaborate across research, software, data, and hardware teams, and mentor engineers.
What they ask for
- Strong experience with PyTorch and efficient GPU use for distributed model training.
- Experience with GPU-accelerated inference using TensorRT or similar frameworks.
- Experience with profiling tools such as NVIDIA's Nsight or PyTorch's Profiler.
- Proficiency in Python and C++, and experience with model compression techniques.
Nice to have
- 10+ years of total experience, including 4+ years working on large-scale model training or inference platforms.
- Demonstrated ability to lead high-performing engineering teams.
Pay
USD 254,000–350,000 (per-year-salary); base salary
Tools
PyTorch, TensorRT, NVIDIA's Nsight, Python, C++
AI focus
Optimizes training and inference performance, model compression, and deployment of VLM, VLA, and foundation models for autonomous driving.
Model-written summary · the original posting is authoritative