Generative AI Research Engineer: Vision & World Models

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

Job summary

TikTok, a global leader in short-form video, is building the Vision-Applied Research team in California to advance generative AI and CV/Multimodal understanding. The role focuses on developing next-generation World Models and scalable training pipelines using massive multimodal datasets to deliver intelligent content creation capabilities.

We seek researchers who can push long-horizon consistency, realistic physics, and interactive real-time systems across cross-functional teams and publications.

Qualifications

• M.S or Ph.D. 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.
• Preferred: experience in video generation and synthesis; diffusion models; 3D/physics-based simulation; or RL for agentic environment interaction.
• Proven first-author publications in CVPR, ICLR, NeurIPS, SIGGRAPH, or ICML.

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

M.S./Ph.D. in Computer Vision/Computer

Multimodal AI

Communication skills

Education

M.S./Ph.D. in CV/CG/ML

Job description

TikTok, a global leader in short-form video, is building the Vision-Applied Research team in California to advance generative AI and CV/Multimodal understanding. The role focuses on developing next-generation World Models and scalable training pipelines using massive multimodal datasets to deliver intelligent content creation capabilities.

We seek researchers who can push long-horizon consistency, realistic physics, and interactive real-time systems across cross-functional teams and publications.