Senior Interactive Vision Model Researcher

Roles & Responsibilities

1.Design and iterate on the next-generation video generation foundation architecture. 2.Explore core technologies for long video generation, including long-context attention, KV Cache compression, and memory mechanisms. 3.Research high-compression-ratio video tokenizers and advance unified modeling capabilities for multi-resolution and multi-frame-rate videos. 4.Lead video pre-training at the 10-100 billion token scale, defining data mixture and curriculum learning strategies. 5.Explore Scaling Laws, define scientific scale-up paths, and continuously improve key model capabilities. 6.Track industry state-of-the-art , lead comparative experiments, drive technical roadmap decisions, and publish academic papers.

Skills Required:

1.Ph.D.in AI-related fields with first-author papers at top-tier conferences. 2.Proficient in the principles and engineering implementation of diffusion models and auto regressive generation. 3.Experience training video/image generation models from scratch; highly proficient inPyTorch and large-scale distributed training. 4.Deep understanding of the design trade-offs in Video VAE/Tokenizers, with 3+ yearsof relevant research experience. 5.Publications related to video generation or diffusion models. 6.Experience in core industry product R&D or hands-on experience with the latest technologies is preferred. 7.Experience leading end-to-end video foundation model projects is preferred.