Machine Learning Engineer - 3D Sensor Simulation

Location: Hybrid in Foster City, California or Seattle, Washington, United States

Company

Zoox develops autonomous vehicle technology and robotics systems designed to improve human mobility.

What you will do

• Design, train, and validate machine learning models that improve the realism of simulated lidar, radar, and camera data.
• Integrate 3DGS and NeRF-based 3D reconstruction with simulation across sensor modalities.
• Build and curate training datasets from real and simulated sensor data, including GenAI-based augmentation.
• Define sensor realism metrics with simulation verification and validation and perception engineers.
• Address sim-to-real gaps that affect autonomous vehicle performance.
• Mentor engineers and interns and establish best practices for training and deploying machine learning models on sensor data.

Requirements

• 3+ years of experience developing machine learning models in Python with PyTorch or TensorFlow.
• Industry experience applying machine learning to lidar, radar, and/or camera data.
• Strong understanding of customizing, tuning, and validating machine learning training pipelines.
• Ability to work in a hybrid setup in Foster City, California, or Seattle, Washington.

Nice to have

• Experience with diffusion, flow matching, VAEs, or other generative techniques.
• Experience with 3D reconstruction, 3DGS, NeRFs, or differentiable rendering.
• Experience developing autonomy for autonomous vehicles, robotics, or computer vision systems.

Culture & Benefits

• Full-time employment within the Software Systems department.
• Collaboration with Synthetic Data, Hardware-in-the-Loop Simulation, simulation verification and validation, and perception teams.
• Work on machine learning and 3D simulation problems supporting autonomous vehicle development.