Research Scientist - World Models

About the role

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically‑grounded 3D environments.

Key responsibilities

• Architect generative world models that reason about space, time, and physics.
• Design and develop image and video diffusion foundational ML models.
• Perform large‑scale distributed model training on cloud infrastructure.
• Develop demos showcasing trained model prototypes.
• Process and maintain large datasets for model training.
• Productionize models and optimise them at test time.

Required profile

• PhD in Computer Science or a related field with top‑tier publications in ML, vision or graphics.
• Strong knowledge of generative models such as image or video diffusion.
• Expertise in cutting‑edge architectures including diffusion transformers (DiT).
• Rich experience with deep learning frameworks, especially PyTorch.
• Expert coding skills and ability to rapidly iterate through ML experiments.

Required skills

• Generative models (image and video diffusion)
• Diffusion transformers (DiT)
• PyTorch