Senior ML Engineer - 3D Perception & Multimodal Fusion

Zoox; Foster City (CA); On-site; USD 150,000 - 230,000; Full time

Job summary

Zoox is seeking a senior researcher/engineer to advance 3D occupancy and segmentation networks. You will design multi-modal fusion (Lidar, Camera, Radar) and build voxel-based or BEV models with temporal coherence for on-vehicle inference.

Collaboration with downstream teams will refine geometry outputs for complex urban driving scenarios. Requires 6+ years in 3D computer vision/ML, proficiency in PyTorch, and experience with TensorRT/CUDA and C++.

Qualifications

• MS or PhD in Computer Science, Robotics, Machine Learning, or related field with 6+ years of industry experience.
• Deep expertise in 3D Computer Vision and Deep Learning, specifically with voxel-based or BEV architectures.
• Strong proficiency in Python and deep learning frameworks (PyTorch) for model training and design; some C++ experience.

Responsibilities

• Design and implement state-of-the-art multi-modal sensor fusion architectures (Lidar, Camera, Radar) to predict 3D occupancy, semantic segmentation, and flow.
• Develop vision-first fusion strategies to enhance geometric understanding and reduce dependency on sparse sensor modalities.
• Engineer temporal processing modules to improve stability and consistency of predictions over time.
• Optimize model architectures for real-time on-vehicle inference, balancing high-fidelity range extension with strict latency constraints.
• Collaborate with downstream consumers (Tracking, Prediction, Planner) to refine geometric outputs for complex maneuvering.

Skills

3D computer vision

BEV architectures

Temporal data sequences

Real-time inference optimization

Education

MS or PhD in CS/Robotics/ML or related

Tools

PyTorch

C++

TensorRT/CUDA

Sparse convolutions

NeRF / Gaussian splats

Job description

Zoox is seeking a senior researcher/engineer to advance 3D occupancy and segmentation networks. You will design multi-modal fusion (Lidar, Camera, Radar) and build voxel-based or BEV models with temporal coherence for on-vehicle inference.

Collaboration with downstream teams will refine geometry outputs for complex urban driving scenarios. Requires 6+ years in 3D computer vision/ML, proficiency in PyTorch, and experience with TensorRT/CUDA and C++.