Student Researcher, Video)
ByteDance
Posted 16 Nov 2026, 05:16 ET · Verified open on LinkedIn 16 Nov, 06:29 ET
This job at a glance
- Who can apply
- New grads and up to 1 year
- Must know
- LLMsComputer visionMachine learningDeep learning
- Work
- Remote
- Pay
- $85 an hour
- Skill demand
- Machine learning10%LLMs8%Computer vision5%Deep learning5%of 99 similar entry-level jobs posted in the US this week
- Listed
- Nov 16, 2026 · still open
Sign in free to see which of these skills your resume already shows.
About the Role
This is a PhD internship opportunity for a 2026 start with the Seed Vision Team at ByteDance, focusing on foundational models for visual generation.
About the Team
The Seed Vision Team develops multimodal generative models and conducts research to solve fundamental computer vision challenges in GenAI. Their work includes researching and developing foundational models for visual generation, ensuring high interactivity and controllability, understanding video patterns, and exploring visual-oriented tasks.
Key Responsibilities
- Develop scalable architectures for long-range video generation with consistent motion, identity, and layout.
- Explore hierarchical or recurrent latent structures to support generation across long temporal spans.
- Address challenges in temporal drift, motion collapse, and high-frequency detail retention.
- Investigate autoregressive or chunked generation strategies that balance quality and memory.
- Design evaluation protocols for long video quality (e.g., realism, consistency, semantic continuity).
Requirements & Tech Stack
Minimum Qualifications:
- Currently pursuing a PhD in Computer Vision, Machine Learning, or a related field.
- Research experience in generative modeling, especially for 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.
Preferred Qualifications:
- Experience with diffusion or transformer-based video models, or long-context sequence generation.
- Familiarity with long-form video datasets.
- Understanding of perceptual metrics and user-study-based video evaluation.
Internship Details
- This is a paid internship with an hourly rate range of $85 - $85.
- Interns receive day one access to health insurance, life insurance, wellbeing benefits, 10 paid holidays per year, and paid sick time.
- Housing allowance may be available for interns not working 100% remote.
- Applications are reviewed on a rolling basis; apply early.
- Clearly state availability (Start date, End date) in your resume.
- The company does not provide sponsorship or any immigration-related benefits for this position.