Machine Learning Engineer - Perception

The Perception team at Zoox is fundamental to our autonomous vehicle technology, creating the understanding of the world for our self-driving robots. We enable safe and efficient navigation in complex environments through sophisticated detection, classification, and tracking systems.

As a member of the Detection, you'll be responsible for helping build sensor fusion models for detecting agents around the robot. You will work on building the vision backbone of the detector by designing sensor fusion models for Zoox's sensor data. You will work on incorporating SOTA language alignment strategies into the per-sensor modality backbones and help Zoox advance faster into new geofences by making the models more generalizable and adaptable to new circumstances.

In this role, you will:

• Train and upgrade current image backbone by performing various studies into incorporating SOTA approaches to be multi-frame, even higher resolution and using large foundational, language-aligned feature encoder
• Deploy temporal image backbone into on-vehicle inference architecture and optimize runtime compute resource;
• Incorporate temporal information into the the existing Zoox’s multi-sensor (Vision, Lidar and Radar) early fusion system to predict object velocity and scene flow
• Develop effective metrics and evaluating algorithm performance with these metrics to demonstrate improvement.
• Collaborate with teams such as ML Optimization, Data Labeling, V&V/Metrics and Planner/Prediction to ensure project is successful for Zoox releases

Qualifications

• Master's degree or PhD in computer science or related field
• Experience with Vision Language Model or multi-modal 3D foundation model.
• Experience with Python and/or C++
• Experience with model deployment with TensorRT
• Proficient in PyTorch model design, implementation, training and evaluation.

Bonus Qualifications

• GPU/CUDA programming experience
• Experience with customized TRT plugin development 
• Experience working with LiDAR, Camera and Radar data

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.
Follow us on LinkedIn
AccommodationsIf you need an accommodation to participate in the application or interview process please reach out to accommodations@zoox.com or your assigned recruiter.
A Final Note:You do not need to match every listed expectation to apply for this position. Here at Zoox, we know that diverse perspectives foster the innovation we need to be successful, and we are committed to building a team that encompasses a variety of backgrounds, experiences, and skills.