Senior Interactive Vision Model Researcher
Core
Design and iterate next-generation video generation foundation architecture, including long-context attention, KV Cache compression, and high-compression-ratio video tokenizers.
Role type
Senior IC machine-learning researcher (video generation)
Builds
Video foundation models and pre-training pipelines
Domain
AI / Computer Vision / Video Generation
Deliverable
production ML models
Required skills
diffusion models, autoregressive generation, PyTorch, large-scale distributed training, video VAE/tokenizers, curriculum learning, scaling laws
Preferred skills
core industry product R&D, leading end-to-end video foundation model projects
Technologies
PyTorch, diffusion models, autoregressive models, video tokenizers
Responsibilities
Design and iterate video generation foundation architecture; Explore long video generation technologies; Lead video pre-training at 10-100 billion token scale; Track industry SOTA and publish academic papers
Seniority
Senior, hands-on IC
