Research Scientist (Generative Modeling)
$250k - $325k • San Francisco • FullTime
Posted 9mo ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Research Engineer
About the job
World Labs is a frontier AI research and product company focused on spatial intelligence, developing world models that perceive, generate, reason, and interact with virtual and physical worlds. Their flagship product, Marble, transforms text, images, and video into navigable 3D worlds, with applications across gaming, film, architecture, robotics, and immersive digital experiences. Backed by leading investors, World Labs is building a world-class team at the intersection of AI research and real-world deployment.
This role is for a talented Research Scientist with a strong background in generative modeling, particularly diffusion models, to join the modeling team. The ideal candidate will have deep expertise in diffusion models applied to images, videos, or 3D assets and scenes. You will collaborate closely with researchers, engineers, and product teams to bring advanced 3D modeling and machine learning techniques into real-world applications, driving projects from conceptualization through to production deployment.
Responsibilities
- Design, implement, and train large-scale diffusion models for generating 3D worlds.
- Develop and experiment with large-scale diffusion models to add novel control signals, adapt to target aesthetic preferences, or distill for efficient inference.
- Collaborate closely with research and product teams to translate product requirements into technical roadmaps.
- Contribute hands-on to all stages of model development including data curation, experimentation, evaluation, and deployment.
- Continuously explore and integrate cutting-edge research in diffusion and generative AI.
- Act as a key technical resource within the team, mentoring colleagues, and driving best practices in generative modeling and ML engineering.
Requirements
- 3+ years of experience in generative modeling or applied ML roles.
- Extensive experience with machine learning frameworks such as PyTorch or TensorFlow, especially in the context of diffusion models and other generative models.
- Deep expertise in at least one area of generative modeling: pre-training, post-training, diffusion distillation, fine-tuning with new conditioning signals, etc for diffusion models.
- Strong history of publications or open-source contributions involving large-scale diffusion models.
- Strong coding proficiency in Python and experience with GPU-accelerated computing.
- Ability to engage effectively with researchers and cross-functional teams, clearly translating complex technical ideas into actionable tasks and outcomes.
- Comfortable operating within a dynamic startup environment with high levels of ambiguity, ownership, and innovation.
- Experience in one or more of the following areas is a strong plus: large-scale model training, data curation for pre-training or post-training, tokenizers and VAEs for image, video, or 3D data, long-context architectures, 3D vision.
Benefits
- Generous health, dental, vision and 401K benefits
- Flexible PTO
- Paid parental leave
- Relocation support as needed