Develop SOTA diffusion models and world-building systems for interactive 3D environments for a well-funded frontier AI startup
Requirements
- Deep expertise in training or fine-tuning SOTA diffusion models and large-scale generative vision systems
- Strong software engineering fundamentals with the ability to transition seamlessly between research prototypes and production systems
- Experience with distributed training, large-scale data curation, or 3D simulation frameworks like Unity or Unreal Engine
Responsibilities
- Lead the training and post-training of state-of-the-art diffusion models for high-fidelity 3D environment synthesis
- Architect distributed training pipelines and data-efficient methods to maximize learning from user interaction and feedback loops
- Optimize large-scale generative vision systems for real-time inference within complex, interactive simulation frameworks
Other
- Benefit from immediate product validation through a massive existing distribution network and partner reach of 250M+ fans
- High-velocity environment with exceptional resources including free housing, food, and transportation for in-person team members
- Location: San Francisco, USA
