World-Model GenAI Research Scientist

TikTok; San Jose (CA); Sur place; USD 162 000 - 388 000; Plein temps

Résumé du poste

TikTok is seeking Research Engineers/Scientists in San Jose to advance world models and large-scale generative AI. You will develop methods and infrastructure to train massive multimodal datasets and ensure long-horizon temporal consistency.

The role emphasizes building data pipelines, training for long-context video generation, and enabling real-time interaction with models. Candidates should have strong background in GenAI, multimodal understanding, and embodied AI.

Qualifications

• MS or PhD in Computer Vision, Computer Graphics, Machine Learning, or equivalent experience.
• Extensive research in GenAI, multimodal foundation models, or Embodied AI.
• Strong communication and collaboration within cross-functional research teams.

Responsabilités

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

Connaissances

GenAI research

Multimodal models

Embodied AI

Communication

Collaboration

Formation

MS/PhD in Computer Vision/Graphics/ML

Description du poste

TikTok is seeking Research Engineers/Scientists in San Jose to advance world models and large-scale generative AI. You will develop methods and infrastructure to train massive multimodal datasets and ensure long-horizon temporal consistency.

The role emphasizes building data pipelines, training for long-context video generation, and enabling real-time interaction with models. Candidates should have strong background in GenAI, multimodal understanding, and embodied AI.