Senior GenAI Research Engineer — Video & World Models

TikTok Inc.; San Jose (CA); On-site; USD 254,000 - 588,000; Full time

Job summary

TikTok Inc. is seeking researchers to build next-generation World Models and scalable multimodal generative systems. You will work on methods and infra to train large-scale generative models from vast multimodal data, focusing on temporal consistency and real-time interaction with users and agents.

The role emphasizes research excellence, collaboration in cross-functional teams, and contributions to video generation, image editing, and world modeling within the Vision-Applied Research group.

Qualifications

• MS or PhD in CV/Graphics/ML or related field.
• At least 3 years research in GenAI, multimodal models, or Embodied AI.
• Strong ability to communicate complex concepts and collaborate with cross-functional research teams.
• Experience in video generation, diffusion models, or 3D/physics-based simulation is a plus.

Responsibilities

• Develop large-scale, diverse, and interactive multimodal data generation pipelines.
• Develop training pipelines for long-context interactive video generation models.
• Advance video generation models for long-horizon temporal consistency and realistic dynamics.

Education

MS or PhD in Computer Vision, Computer Graphics, ML, or related field

Job description

TikTok Inc. is seeking researchers to build next-generation World Models and scalable multimodal generative systems. You will work on methods and infra to train large-scale generative models from vast multimodal data, focusing on temporal consistency and real-time interaction with users and agents.

The role emphasizes research excellence, collaboration in cross-functional teams, and contributions to video generation, image editing, and world modeling within the Vision-Applied Research group.