World Labs
Research Scientist (Generative Modeling)
$250K–$325K
San Francisco · On-site · Full-time · Posted Dec 29, 2025
- Experience
- 3+ years in generative modeling or applied ML roles.
- Visa sponsorship
- Visa sponsorship is offered; success is not guaranteed for every candidate or role.
About the job
Conduct hands-on research and engineering to develop, train, and deploy diffusion models that generate controllable 3D worlds.
What you'll do
- Design, implement, and train large-scale diffusion models for 3D world generation, including adding controls, adapting aesthetics, and distilling models for efficient inference.
- Contribute to data curation, experimentation, evaluation, and deployment; translate product needs into technical roadmaps.
- Explore and integrate generative AI research, and mentor colleagues on generative modeling and ML engineering practices.
What they ask for
- Extensive experience with machine learning frameworks, especially for diffusion and other generative models.
- Deep expertise in at least one area of diffusion modeling, such as pre-training, post-training, distillation, or fine-tuning with new conditioning signals.
- Strong history of publications or open-source contributions involving large-scale diffusion models.
- Proficiency in Python and experience with GPU-accelerated computing.
Nice to have
- Large-scale training infrastructure, production model integration, or involvement in developing or training state-of-the-art generative models.
- Open-source contributions in computer vision, graphics, or ML.
Pay
$250K – $325K (base salary)
Tools
diffusion models, PyTorch, TensorFlow, Python, GPU-accelerated computing
AI focus
Generative AI research and development, especially diffusion models for generating 3D worlds with novel controls, aesthetic adaptation, and efficient inference.
Model-written summary · the original posting is authoritative