ByteDance
Student Researcher - (Seed Model - Video) – 2026 Start (PhD)
San Jose, California · Internship · Posted Oct 28, 2026
- Education
- Currently pursuing a PhD in Computer Vision, Machine Learning, or a related field.
- Visa sponsorship
- Candidates must be able to establish authorization to work in the United States; the company does not provide sponsorship or immigration-related benefits.
About the job
Develop research and architectures for long-range video generation, improving temporal consistency, visual quality, memory efficiency, and evaluation.
What you'll do
- Develop scalable architectures for long-range video generation with consistent motion, identity, and layout.
- Investigate temporal structures and autoregressive or chunked strategies to address generation quality and memory challenges.
- Design evaluation protocols for long-video realism, consistency, and semantic continuity.
What they ask for
- Currently pursuing a PhD in Computer Vision, Machine Learning, or a related field.
- Research experience in generative modeling, especially video, motion, or temporal sequences.
- First-author publications in CVPR, ICCV, ECCV, NeurIPS, ICLR, or ICML.
- Proficiency in deep learning frameworks and experience with large-scale video datasets.
Nice to have
- Experience with diffusion or transformer-based video models, or long-context sequence generation.
- Familiarity with long-form video datasets and perceptual metrics or user-study-based video evaluation.
AI focus
Research and develop generative foundational models for long-range video generation, including temporal consistency and evaluation.
Model-written summary · the original posting is authoritative