Zoox
Senior Machine Learning Engineer - Perception 3D Segmentation
$254K–$350K
Foster City, CA · Hybrid · Senior · Full-time · Posted Jul 17, 2026
- Experience
- 6+ years of industry experience.
- Education
- MS or PhD in Computer Science, Robotics, Machine Learning, or related field.
About the job
Develop and optimize multimodal 3D occupancy and segmentation models that provide temporally consistent environmental representations for autonomous vehicles.
What you'll do
- Design sensor-fusion architectures to predict 3D occupancy, semantic segmentation, and flow.
- Develop temporal processing and vision-first fusion strategies to improve geometric understanding and prediction consistency.
- Optimize models for real-time on-vehicle inference and refine geometric outputs with downstream teams.
What they ask for
- MS or PhD in Computer Science, Robotics, Machine Learning, or a related field.
- Deep expertise in 3D Computer Vision and Deep Learning, particularly voxel-based or BEV architectures.
- Proficiency in Python and PyTorch, plus some experience in C++.
- Experience with multimodal sensor fusion and temporal data sequences.
Nice to have
- Experience optimizing models with TensorRT/CUDA or familiarity with sparse convolutions or query-based architectures.
- Experience with Vision Language Model, multi-modal 3D foundation model, World Model, or VLA.
Pay
USD 254,000–350,000 per-year-salary (base salary)
Tools
Lidar, Camera, Radar, Python, PyTorch, C++, TensorRT, CUDA
AI focus
Build deep-learning models for multimodal 3D occupancy, semantic segmentation, flow, and temporally consistent scene understanding for autonomous driving.
Model-written summary · the original posting is authoritative