Research Scientist - 3D Vision and Generation, Self-Driving
Core
Conduct research on 3D vision, reconstruction, and generation for autonomous systems and robotics, focusing on foundation models and world-action models.
Role type
Research Scientist (3D Vision and Generation)
Builds
Next-generation physical AI for autonomous driving and robotic generalists
Domain
Autonomous driving, robotics, computer vision, machine learning
Deliverable
production ML models
Required skills
3D vision, 3D reconstruction, 3D generation, multi-modal pretraining, Gaussian splatting, world foundation models, Python, PyTorch, distributed machine learning training
Preferred skills
3D foundation model and pretraining, multi-modal foundation model, feed-forward Gaussian splatting, world foundation model and generation, 3D/multi-view end-to-end models
Technologies
Python, PyTorch
Responsibilities
Conduct research on 3D vision related topics including 3D/world-action foundation models and multi-modal pretraining; Work closely with other Research Scientists and interns on research publications for submission to top-tier conferences; Collaborate with Research Engineers and engineering teams to test and deploy algorithms to autonomy and simulation products
Seniority
Open to all years of experience, potential Tech Lead and Manager capacity
