Machine Learning Engineer - 3D Sensor Simulation

Zoox is building for autonomous vehicle simulation and training, and the 3D Sensor Simulation team plays a key role in making simulated sensor data more realistic. As a Machine Learning Engineer, you will develop machine learning models and data pipelines that improve the fidelity of simulated lidar, radar, and camera signals, helping advance training and testing for autonomy.

What you’ll do

• Design, train, and validate ML models that increase the realism of simulated lidar, radar, and camera data used in AV simulation pipelines.
• Work with Synthetic Data and HIL Sim teams to integrate 3DGS and NeRF-based 3D reconstruction alongside simulation for all sensor modalities.
• Build and curate training datasets from real and simulated sensor data, including GenAI-based data augmentation.
• Partner with Sim V&V and Perception engineers to define sensor realism metrics and focus efforts on closing sim-to-real gaps with the most impact to autonomy.
• Mentor engineers and interns, and help establish best practices for training and deploying ML models on Zoox sensor data.

Requirements

• 3+ years of experience developing ML models in Python using PyTorch or TensorFlow.
• Industry experience applying ML to sensor data (lidar, radar, and/or cameras).
• Strong understanding of customizing, tuning, and validating ML training pipelines.

Technologies and tools

• Python, PyTorch, TensorFlow
• 3DGS, NeRFs
• GenAI-based data augmentation
• Diffusion, flow matching, VAEs

Compensation and location

This onsite role is based in Seattle, WA. The salary range is USD 189,000 - 283,000 per yearly, and the posting notes that compensation includes multiple components: salary, Amazon Restricted Stock Units (RSUs), and Zoox Stock Appreciation Rights. A sign-on bonus may be offered as part of the compensation package. The base salary range applies only to salary, and actual compensation can vary by geography, level, and factors including relevant years of experience, domain knowledge, and interview performance.

Benefits

• Paid time off (including sick leave, vacation, and bereavement)
• Unpaid time off
• Zoox Stock Appreciation Rights
• Amazon RSUs
• Health insurance
• Long-term care insurance
• Long-term and short-term disability insurance
• Life insurance
• A sign-on bonus may be offered

Additional qualifications

• Experience with generative techniques such as diffusion, flow matching, or VAEs.
• Experience with 3D reconstruction (3DGS, NeRFs) or differentiable rendering.
• Prior experience developing autonomy in AVs or other robotics and computer vision.

Accommodations and application notes

• If you need an accommodation for the application or interview process, reach out to [email protected] or your assigned recruiter.
• You do not need to match every listed expectation to apply.
• Zoox may use AI tools during hiring to support parts of the process, including reviewing applications, analyzing resumes, and assessing responses to identify potential inconsistencies. Final hiring decisions are made by humans.