> Markdown version of [/jobs/ext/4252882-machine-learning-engineer-3d-sensor-simulation](https://www.wearedevelopers.com/jobs/ext/4252882-machine-learning-engineer-3d-sensor-simulation). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Machine Learning Engineer - 3D Sensor Simulation

- **Company:** Zoox
- **Location:** Foster, United States
- **Experience:** Experienced
- **Contract:** Permanent contract
- **Skills:** 3D Scanning, Computer Vision, Python (Programming Language), Machine Learning, Performance Tuning, NeRF (Neural Radiance Fields), Tensorflow, Pytorch, Variational Autoencoders, Stable Diffusion
- **Published:** October 13, 2026
- **Apply:** https://startup.jobs/machine-learning-engineer-3d-sensor-simulation-zoox-10420559

## About the Role

* 3+ years of experience developing ML models in Python with PyTorch or TensorFlow
 * Industry experience applying ML to sensor data (lidar, radar, and/or cameras)
 * Solid understanding of customizing, tuning, and validating ML training pipelines, * 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 About ZooxZoox is developing the first ground-up, fully autonomous vehicle fleet and the supporting ecosystem required to bring this technology to market. Sitting at the intersection of robotics, machine learning, and design, Zoox aims to provide the next generation of mobility-as-a-service in urban environments. We're looking for top talent that shares our passion and wants to be part of a fast-moving and highly execution-oriented team.

## Description

* Design, train, and validate ML models that improve the realism of simulated lidar, radar, and camera data in autonomous vehicle (AV) simulation pipelines.
 * Collaborate with Synthetic Data and HIL Sim teams to integrate 3DGS and NeRF-based 3D reconstruction with simulation of 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 close the sim-to-real gaps with the greatest impact on autonomy.
 * Mentor engineers and interns, and establish best practices for training and deploying ML on Zoox sensor data.