Research Engineer: Generative AI & World Models

TikTok Inc.; San Jose (CA); On-site; USD 162,000 - 388,000; Full time

Benefits offered by this job

Medical/dental/vision

401(k) match

Parental leave

Disability insurance

Life insurance

Wellbeing benefits

Job summary

TikTok Inc. is seeking Research Engineer/Scientists for the Vision-Applied Research team to develop next-generation World Models and multimodal AI systems.

You will work on scalable data generation pipelines and long-horizon video synthesis with real-time interaction capabilities. We value strong publication records and collaboration across cross-functional teams, with opportunities to influence research directions and product impact.

Qualifications

• M.S or Ph.D. in Computer Vision, Computer Graphics, Machine Learning, or equivalent experience.
• Extensive research in GenAI, multimodal foundation models, or Embodied AI.
• Proven ability to communicate complex concepts and collaborate cross-functionally.

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 to capture long-horizon temporal consistency and realistic dynamics.

Skills

Communicating concepts

Cross-functional collaboration

Education

M.S. or Ph.D. in Computer Vision/ML/CG

Job description

TikTok Inc. is seeking Research Engineer/Scientists for the Vision-Applied Research team to develop next-generation World Models and multimodal AI systems.

You will work on scalable data generation pipelines and long-horizon video synthesis with real-time interaction capabilities. We value strong publication records and collaboration across cross-functional teams, with opportunities to influence research directions and product impact.