Generative AI Research Engineer - Video World Models

TikTok; San Jose (CA); On-site; USD 156,000 - 388,000; Full time

Job summary

TikTok is seeking Research Engineer / Scientist for the Vision-Applied Research team to advance generative AI and CV/multimodal understanding. You will help build next-generation World Models and scale infrastructure for training on massive multimodal datasets.

The role emphasizes long-horizon video generation, realistic physics, complex dynamics, and real-time user interactions with models, with collaboration across research groups for impactful breakthroughs.

Qualifications

• MS or PhD in Computer Vision, Computer Graphics, Machine Learning, or equivalent experience.
• Extensive research experiences in broad GenAI, multimodal foundation models, or Embodied AI areas.
• Demonstrated ability to communicate complex technical concepts and collaborate effectively within cross-functional research teams

Responsibilities

• Develop large-scale, diverse, and interactive multi-modal data generation pipeline.
• Develop training pipeline for long-context interactive video generation models.
• Advance video generation models to capture long-horizon temporal consistency, realistic physical dynamics, object interactions, and causal relationships from large-scale multi-modal data.

Skills

GenAI research

Multimodal models

Communication

Education

MS or PhD in Computer Vision / ML

Job description

TikTok is seeking Research Engineer / Scientist for the Vision-Applied Research team to advance generative AI and CV/multimodal understanding. You will help build next-generation World Models and scale infrastructure for training on massive multimodal datasets.

The role emphasizes long-horizon video generation, realistic physics, complex dynamics, and real-time user interactions with models, with collaboration across research groups for impactful breakthroughs.