Tech Stack

Description

You will advance controllable 3D content creation by developing state-of-the-art generative models, building scalable training pipelines, and publishing at top venues.

Requirements

• PhD in Machine Learning, Computer Vision, or Computer Graphics
• Published work on diffusion, flow-matching, or score-based generative models
• Strong engineering skills with PyTorch, JAX, or CUDA-level optimization
• Understanding of 3D representations and differentiable rendering
• Ability to scale experiments and communicate complex results

Responsibilities

• Conduct research on flow-matching, diffusion, and score-based methods for 3D generation
• Design scalable training pipelines for controllable 3D generation (meshes, Gaussians, NeRFs, voxels, implicit fields)
• Develop conditioning and control techniques (text, sketch, pose, camera, physics) and multi-view consistency
• Analyze model behavior through ablations, visualizations, and metrics
• Collaborate with cross-disciplinary teams to translate research into production systems