CareerPlanSign in

Video Generation Foundation Model Researcher

Singapore-CapitaSky💼 Full-time🗓 2026-07-17 → 2026-09-26

Core

Design and iterate next-generation video generation foundation architecture, focusing on long video generation, high-compression tokenizers, and unified modeling for multi-resolution/multi-frame-rate videos.

Role type

Senior IC video generation foundation model researcher

Builds

Production video foundation models for next-gen gaming experiences

Domain

AI research, video generation, diffusion models, large-scale distributed training

Deliverable

production ML models

Required skills

diffusion models, autoregressive generation, PyTorch, large-scale distributed training, video VAE/tokenizer 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 tokenizers, KV Cache compression

Responsibilities

Design and iterate video generation foundation architecture; explore long-context attention and memory mechanisms; lead pre-training at 10-100 billion token scale; track SOTA and publish academic papers

Seniority

Senior, hands-on IC

Sourced via workday · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.