Job Description
AI Researcher – Video World Generation San Francisco (Bay Area)
Help build the next generation of AI video systems that can create rich, interactive worlds from text or images.
What you’ll work on:
- Foundational diffusion models and world models for high-quality video generation
- Real-time AI pipelines that turn ideas into consistent, dynamic video scenes
- Multi-agent systems and orchestration for intelligent video creation
- RL techniques for more adaptive and open-ended video generation
Required:
- Strong production experience with large multimodal or agentic AI systems
- Hands-on work with distributed training or large-scale vision/diffusion pipelines
Bonus (big plus):
- Experience training or fine-tuning diffusion models
- Background in world models, simulation, robotics, or multi-agent systems
- Familiarity with game engines (Unity/Unreal) as test environments