Beschreibung

In this role, you will tackle the complexities of generative AI by training models to understand 3D space, developing innovative conditioning mechanisms, and conducting experiments that shape the future of AI-generated content.

Anforderungen

• •Understanding of projective geometry
• •Hands-on experience training large-scale diffusion models
• •Strong foundations in 3D projective geometry
• •Experience with 3D-aware generative models or neural rendering techniques
• •Track record of integrating geometric priors into neural networks
• •Deep proficiency in PyTorch and modern deep learning
• •Solid understanding of distributed training techniques
• •Experience with camera calibration, structure-from-motion, or SLAM
• •Published research at the intersection of 3D vision and generative models
• •Understanding of tradeoffs between different 3D representations

Aufgaben

• •Train large-scale diffusion transformer models for camera-controllable image and video generation
• •Develop conditioning mechanisms for diffusion models to understand 3D camera parameters
• •Conduct experiments to analyze design choices for 3D control and communicate insights
• •Evaluate speed-quality tradeoffs of 3D-aware architectures in production settings

Tools & Technologien