Machine Learning Engineer - Vision Foundation Models
Core
Design, train, and evaluate vision-based in-cabin perception models to understand passengers, objects, and behaviors inside the vehicle for rider safety and robotaxi operations.
Role type
Senior IC machine learning engineer (vision foundation models)
Builds
Vision models for in-cabin perception (detection, pose, action recognition) deployed on robotaxi systems
Domain
Autonomous vehicles / Computer Vision
Deliverable
production ML models
Required skills
Computer vision, deep learning, object detection, pose estimation, action recognition, vision-transformer detectors, self-supervised learning, foundation models, Python, PyTorch, data curation, labeling guidelines, metric design, error analysis
Preferred skills
In-cabin monitoring, multi-camera/fisheye imagery, low-light conditions, TensorRT, ONNX, C++, vision-language models, synthetic data, auto-labeling
Technologies
PyTorch, Python, TensorRT, ONNX, DINOv3
