PhD Intern: Multimodal AI & World Modeling

Bytedance; San Jose (CA); On-site; USD 97,000 - 138,000; Full time

Benefits offered by this job

Health insurance

Life insurance

Wellbeing benefits

10 paid holidays per year

Paid sick time

Housing allowance

Job summary

ByteDance Seed team seeks PhD interns to design RL training systems for multimodal foundation models and to develop unified frameworks for audiovisual and language integration. The role emphasizes visual latent reasoning and collaboration with researchers on world modeling and instruction-conditioned generation.

Applicants should be PhD candidates with publications in leading AI/ML venues and a strong RL/multimodal research background, ready to start in the United States under a campus

Qualifications

• Pursuing a PhD in a related technical discipline.
• Publications in top AI/ML venues (CVPR, ECCV, ICCV, NeurIPS, ICLR, ICML).
• Strong research background in RL, multimodal learning, video understanding or vision-language modeling.
• Must have work authorization in the country of employment at the time of hire.

Responsibilities

• Design and implement RL training systems for large-scale multimodal models.
• Develop unified modeling frameworks integrating video, audio, and language for visual latent reasoning.
• Explore RL-based approaches for multimodal visual reasoning and generation.
• Collaborate with researchers to evaluate models on world modeling, reasoning, and instruction-conditioned generation.

Skills

Reinforcement learning

Multimodal learning

Video understanding

Vision-language modeling

Education

PhD in Software Development, Computer Science, Computer Engineering or related technical discipline

Job description

ByteDance Seed team seeks PhD interns to design RL training systems for multimodal foundation models and to develop unified frameworks for audiovisual and language integration. The role emphasizes visual latent reasoning and collaboration with researchers on world modeling and instruction-conditioned generation.

Applicants should be PhD candidates with publications in leading AI/ML venues and a strong RL/multimodal research background, ready to start in the United States under a campus