Zoox
Software Engineer, ML Inference Optimization
$177K–$270K
Foster City, CA · On-site · Full-time · Posted May 28, 2026
- Experience
- 4+ years total experience, including 2+ years working on large-scale model training or inference platforms.
About the job
Optimizes ML training and inference systems so large models can run efficiently in Zoox robotaxis.
What you'll do
- Design, implement, and operate performance optimization techniques for VLM, VLA, and foundation models.
- Collaborate with research, software, data, and hardware teams on requirements and architecture.
- Improve ML tools, model development, and serving systems for in- and off-vehicle use cases.
What they ask for
- Experience with training frameworks such as 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 or C++.
Pay
USD 177,000–270,000 (per-year-salary) base salary
Tools
PyTorch, GPUs, TensorRT, NVIDIA's Nsight, PyTorch's Profiler, Python, C++
AI focus
ML training and inference optimization for VLMs, VLAs, and foundation models, including efficient deployment in autonomous robotaxis.
Model-written summary · the original posting is authoritative