Interactive Vision Model Research Intern
Core
Research and design next-generation video generation foundation models, focusing on long-context attention, KV Cache compression, and high-compression video tokenizers.
Role type
Research Intern (Video Generation Foundation Models)
Builds
Next-generation video generation foundation models for games
Domain
AI / Computer Vision / Video Generation
Deliverable
production ML models
Required skills
Diffusion models, autoregressive generation, PyTorch, large-scale distributed training, Video VAE/Tokenizers design, curriculum learning, Scaling Laws analysis
Preferred skills
End-to-end video foundation model project leadership, core industry product R&D experience
Technologies
PyTorch, Diffusion models, Autoregressive models, Video VAE, Tokenizers
Responsibilities
Design and iterate video generation foundation architecture, explore long video generation technologies, research high-compression video tokenizers, lead video pre-training, explore Scaling Laws, track state-of-the-art and publish academic papers
Seniority
Intern, Research
