PhD Research Intern — Long-Video Generation

Bytedance

San Jose (CA)

On-site

USD 97,000 - 138,000

Part time

4 days ago
Be an early applicant
Application generator

An application made for this job — a tailored resume and cover letter that speak straight to the posting.

Get past ATS filters

Benefits offered by this job

Health insurance
Paid holidays
Housing allowance
Wellbeing benefits

Job summary

ByteDance Seed Team seeks PhD interns to advance foundational models for visual generation and long-range video synthesis. You will contribute to research and development of multimodal generative models, with an emphasis on interactivity and controllability in video creation.

The program blends hands-on work, community-building, and mentorship, offering exposure to cutting-edge AI research and real-world applications in GenAI. Strong publication record is valued.

Qualifications

  • PhD candidate in Computer Vision or ML required.
  • Research experience in generative modeling for video or temporal sequences.
  • First-author publications in top CV/ML conferences.
  • Proficiency with deep learning frameworks and large video datasets.

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 temporal drift, motion collapse, and high-frequency detail retention challenges.
  • Investigate autoregressive or chunked generation strategies balancing quality and memory.
  • Design evaluation protocols for long video quality and semantic continuity.

Skills

PhD candidate in CV/ML
Video generative modeling research
Publications in CVPR/ICCV/NeurIPS/ICML
Deep learning frameworks (PyTorch)

Education

PhD in Computer Vision or ML

Job description

ByteDance Seed Team seeks PhD interns to advance foundational models for visual generation and long-range video synthesis. You will contribute to research and development of multimodal generative models, with an emphasis on interactivity and controllability in video creation.

The program blends hands-on work, community-building, and mentorship, offering exposure to cutting-edge AI research and real-world applications in GenAI. Strong publication record is valued.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Research Scientist, Multimodal & Foundation Models
Research Scientist, Multimodal & Foundation Models

Bytedance • San Jose (CA)

On-site
USD 254,000 - 480,000
Medical/Dental/Vision
401(k) with company match
Paid parental leave
+6
Research Scientist, Vision & Multimodal AI
Research Scientist, Vision & Multimodal AI

Bytedance • San Jose (CA)

On-site
USD 254,000 - 480,000
Healthcare benefits
401(k) with match
Paid parental leave
+3
Graduate GenAI Research Scientist — Multimodal Vision
Graduate GenAI Research Scientist — Multimodal Vision

Bytedance • San Jose (CA)

On-site
USD 162,000 - 317,000
Medical insurance
Dental insurance
Vision insurance
+8
PhD Intern: Multimodal AI & World Modeling
PhD Intern: Multimodal AI & World Modeling

Bytedance • San Jose (CA)

On-site
USD 97,000 - 138,000
Health insurance
Life insurance
Wellbeing benefits
+3
Student Researcher (Seed Vision – Long-Range Video Generation) – 2026 Start (PhD)
Student Researcher (Seed Vision – Long-Range Video Generation) – 2026 Start (PhD)

ByteDance • San Jose (CA)

On-site
USD 41,000 - 69,000
GenAI Research Scientist - Multimodal Video & AI
GenAI Research Scientist - Multimodal Video & AI

TikTok • San Jose (CA)

On-site
USD 162,000 - 317,000
Medical, dental, and vision insurance
401(k) with company match
Paid parental leave
+6
PhD Internship: LLM & Multimodal AI Researcher
PhD Internship: LLM & Multimodal AI Researcher

Bytedance • San Jose (CA)

On-site
USD 97,000 - 138,000
Health insurance
Housing allowance
Graduate Research Scientist — Multimodal AI
Graduate Research Scientist — Multimodal AI

Bytedance • San Jose (CA)

On-site
USD 254,000 - 480,000
Research Scientist Graduate (Foundation Model, Generative AI) - 2025 Start (PhD)
Research Scientist Graduate (Foundation Model, Generative AI) - 2025 Start (PhD)

ByteDance • Seattle (WA)

On-site
USD 198,360 - 416,100
PhD Research Intern: Generative AI & Multimodal Models
PhD Research Intern: Generative AI & Multimodal Models

NVIDIA Corporation • Santa Clara (CA)

On-site
USD 41,000 - 129,000
Intern benefits