Research Scientist - World Models

The role

The Research Scientist will architect generative world models that reason about space, time, and physics. This role involves designing image/video diffusion models and performing large-scale distributed model training.

What you will do

• Architect generative world models that reason about space, time, and physics.
• Design and develop image/video diffusion foundational ML models.
• Large-scale distributed model training on top of distributed cloud infra.
• Develop demos showcasing the trained model prototypes.
• Processing and maintaining large data for model training.
• Productionizing models, test-time model optimization.

Required qualifications

• PhD in Computer Science or related field with a top-tier publication record in ML, Vision or graphics (CVPR, ECCV/ICCV, NeurIPS, SIGGRAPH, etc.)
• Strong knowledge of generative models such as image or video diffusion
• Strong knowledge of cutting-edge architectures including diffusion transformers (DiT)
• Rich experience with deep learning frameworks such as PyTorch
• Expert coding skills
• Ability to rapidly iterate through ML experiments, including usage of modern AI coding tools

About the company

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. The mission is to redefine how industries generate and interact with physically-grounded 3D environments.