Research Scientist - 3D Diffusion

The role

You will lead research to design, build, train, evaluate, and optimize diffusion-based generative models. These models will produce high-quality 3D content from images, video, and other inputs.

What you will do

• Design and develop diffusion-based methods for 3D generation from images, video, and other inputs.
• Build, train, optimize, and evaluate 3D diffusion models.
• Apply and adapt cutting-edge image and video diffusion backbones to 3D generation.
• Implement and experiment with state-of-the-art 3D representations including point clouds, meshes, and 3D Gaussian Splatting.
• Develop training pipelines and loss functions.
• Collaborate with researchers to integrate physics-aware priors and world model capabilities into diffusion systems.
• Analyze model performance, debug failure cases, and iterate rapidly.

Required qualifications

• PhD in computer science, computer vision, graphics, machine learning, or a related field.
• Top-tier publication record at venues such as CVPR, ECCV/ICCV, NeurIPS, and SIGGRAPH.
• Strong fundamentals in deep learning and generative modeling, in particular diffusion models and large transformer models.
• Hands-on experience training diffusion models and working with cutting-edge image and video model stacks.
• Solid understanding of 3D processing concepts such as camera geometry, depth, reconstruction, point clouds, meshes, or Gaussian splats.
• Proficiency in Python and deep learning frameworks such as PyTorch.
• Experience in large-scale model training and optimization.
• Ability to implement research ideas, run rigorous experiments, and ship reliable ML code.

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.