Research Engineer - 3D Vision and Generation, Self-Driving
Core
Researching 3D vision, foundation models, and multi-modal pretraining for end-to-end autonomous driving and robotic systems.
Role type
Research Engineer (3D Vision & Generation)
Builds
End-to-end algorithms for mass production vehicles, neural simulation/generation tools, and 3D foundation models.
Domain
Autonomous driving, robotics, computer vision, machine learning
Deliverable
production ML models | research
Required skills
3D reconstruction, Gaussian splatting, 3D/multi-modal foundation models, world foundation models, video generation, Python, PyTorch, distributed machine learning training
Preferred skills
MSc or PhD in machine learning/computer vision, industry experience in self-driving applications
Technologies
Python, PyTorch, Gaussian splatting, 3D foundation models
Responsibilities
Conduct research on 3D vision topics including 3D foundation models and multi-modal pretraining; Collaborate with engineering teams to deploy end-to-end algorithms for mass production vehicles; Work with scientists on high-quality research publications for top-tier conferences.
