Research Scientist - Generative Diffusion for 3D Worlds

World Labs; San Francisco (CA); On-site; USD 250,000 - 325,000; Full time

Job summary

World Labs in San Francisco is seeking a Research Scientist with a strong background in diffusion models and generative ML to advance 3D world modeling. You will work closely with researchers, engineers, and product teams to push the frontier of spatial intelligence.

You will design and train large-scale diffusion systems, explore novel conditioning signals, and help deploy models in real-world applications, while contributing to open-source efforts and publications.

Qualifications

• 3+ years in generative modeling or applied ML roles, preferably in fast-paced research environments.
• Extensive experience with ML frameworks such as PyTorch or TensorFlow, in diffusion or other generative models.
• Deep expertise in at least one area of generative modeling (pre-training, post-training, distillation, conditioning signals).
• Strong history of publications or open-source contributions related to diffusion models.
• Strong coding in Python and GPU-accelerated computing.
• Ability to collaborate with researchers and product teams to translate requirements into roadmaps.
• Comfortable in a startup with ambiguity and ownership.

Responsibilities

• Design, implement, and train large-scale diffusion models for generating 3D worlds.
• Develop and experiment with diffusion models to add novel control signals and efficient inference.
• Collaborate with research and product teams to translate requirements into technical roadmaps.
• Contribute hands-on to data curation, experimentation, evaluation, and deployment.
• Continuously explore cutting-edge diffusion and generative AI research.
• Mentor colleagues and drive best practices in ML engineering.

Skills

Diffusion models

ML frameworks

3D vision

Large-scale training

Python

Publications

Startup experience

Tools

PyTorch

TensorFlow

GPU clusters

Distributed training

Job description

World Labs in San Francisco is seeking a Research Scientist with a strong background in diffusion models and generative ML to advance 3D world modeling. You will work closely with researchers, engineers, and product teams to push the frontier of spatial intelligence.

You will design and train large-scale diffusion systems, explore novel conditioning signals, and help deploy models in real-world applications, while contributing to open-source efforts and publications.