Research Scientist, Real-Time DiT Video Models

📋 Description

• Design and optimize AI video generation models using diffusion.
• Develop state-of-the-art algorithms for video content.
• Work with teams on large video datasets (motion, gestures, faces).
• Experiment with diffusion architectures for high-quality synthesis.
• Define validation strategies and metrics for synthetic vs real gameplay.
• Stay on the bleeding edge of CVPR/NeurIPS/ICML/ICCV and align with roadmap.

🎯 Requirements

• PhD in Computer Vision, Machine Learning, or a closely related field.
• Hands-on experience with research of video diffusion models.
• Publications at top-tier conferences (CVPR, NeurIPS, ICCV, ICML, SIGGRAPH).
• Real-time video generation experience is a plus.
• Proficiency in Python and PyTorch.
• Strong knowledge of CNNs, Transformers, and diffusion/autoregressive models.