Research Scientist – Controlled 3d Generation

Stabilityai

Remote
Remote
Flow matching
Diffusion models
Score-based methods
StabilityAI is seeking a remote Research Scientist specialized in 3D generation, flow matching, and diffusion models. The ideal candidate will conduct advanced research, develop scalable training pipelines, and collaborate with various teams to create controllable 3D content

Job Summary

  • You’ll help advance the frontier of controllable 3D content creation—building models that generate consistent, editable, and physically grounded 3D assets and scenes.
  • Conduct cutting-edge research on flow-matching, diffusion, and score-based methods for 3D generation and reconstruction.
  • Develop techniques for conditioning and control (text, sketch, pose, camera, physics) and multi-view consistency.

Matching Summary

Match Score: 85

StabilityAI is seeking a remote Research Scientist specialized in 3D generation, flow matching, and diffusion models. The ideal candidate will conduct advanced research, develop scalable training pipelines, and collaborate with various teams to create controllable 3D content.

Skills & Requirements

Must-have

  • flow matching
  • diffusion models
  • score-based methods
  • 3D generation
  • PyTorch
  • JAX
  • CUDA-level optimisation

Nice-to-have

  • coherent 3D scenes
  • scene-level control
  • physically-based rendering
  • world-model architectures

Key Requirements

  • PhD in Machine Learning, Computer Vision, or Computer Graphics
  • Published work on diffusion, flow-matching, or score-based generative models
  • Understanding of 3D representations
  • Solid grasp of geometry processing
  • Solid grasp of multi-view consistency
  • Solid grasp of differentiable rendering

Work Rights

Not specified

Tailored Resume

Cover Letter