Senior GenAI & Vision Research Engineer

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

Job summary

TikTok's Vision-Applied Research team focuses on Generative AI and CV/Multimodal understanding to enable users to create and share content easily. You will help build scalable data pipelines and training systems for long-context video generation.

Ideal candidates have a MS/PhD in a relevant field, 3+ years in GenAI or multimodal research, and a proven ability to communicate complex ideas across teams in a fast-paced environment.

Qualifications

• MS/PhD in Computer Vision, Computer Graphics, ML or equivalent.
• 3+ years research in GenAI, multimodal foundation models, or Embodied AI.
• Strong ability to communicate complex concepts and collaborate with cross-functional teams.

Responsibilities

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

Skills

GenAI research

Communication

Collaboration

Education

M.S./ Ph.D. in relevant field

Job description

TikTok's Vision-Applied Research team focuses on Generative AI and CV/Multimodal understanding to enable users to create and share content easily. You will help build scalable data pipelines and training systems for long-context video generation.

Ideal candidates have a MS/PhD in a relevant field, 3+ years in GenAI or multimodal research, and a proven ability to communicate complex ideas across teams in a fast-paced environment.