Senior Researcher, Video Generation Foundation Model Researcher｜高级研究员-视频生成模型
Core
Design and iterate next-generation video generation foundation architectures, leading pre-training at 10-100 billion token scales and exploring core technologies for long video generation.
Role type
Senior Researcher, Video Generation Foundation Model
Builds
Video generation foundation models and pre-training pipelines
Domain
AI, Video Generation, Diffusion Models
Deliverable
production ML models
Required skills
Diffusion models, autoregressive generation, PyTorch, large-scale distributed training, Video VAE/Tokenizers, curriculum learning, Scaling Laws
Preferred skills
End-to-end video foundation model project leadership, core industry product R&D
Technologies
PyTorch, diffusion models, autoregressive models, Video VAE, Tokenizers
Responsibilities
Design and iterate next-generation video generation foundation architecture; Explore core technologies for long video generation including long-context attention and KV Cache compression; Research high-compression-ratio video tokenizers; Lead video pre-training at 10-100 billion token scale; Explore Scaling Laws and define scientific scale-up paths; Track industry state-of-the-art and publish academic papers.