About the role#
The Seed Multimodal Interaction and World Model team develops models with human-level multimodal understanding and interaction capabilities. We focus on advancing multimodal assistant products. As an intern, you will contribute to our research and future technology plans while working alongside industry experts.
What you'll need#
- Currently pursuing a PhD in Computer Science, Mathematics, Electrical Engineering, Computer Engineering, or a related field.
- Strong programming skills and a solid foundation in algorithms and data structures.
- Proficiency in Python or C/C++.
- A research track record with publications in conferences related to artificial intelligence, machine learning, or multimodal learning.
- Experience in multimodal modeling, vision-language modeling, world modeling, simulation, or 3D representations.
- Experience with latent space modeling or structured representations is a plus.
- Ability to solve problems and conduct independent research.
- Ability to collaborate effectively in a research environment.
What you'll do#
- Conduct research on multimodal foundation models and related systems.
- Explore methods to improve model capabilities in areas like vision-language modeling, world modeling, and representation learning.
- Design and prototype algorithms, models, or system components.
- Collaborate with the team to advance research directions.
Location & details#
- Location: San Jose, California.
- Modality: On-site.
- Employment: Full-time internship.
- Term: Rolling basis.
- Compensation: $85 per hour.
- Note: Candidates must be authorized to work in the United States. Sponsorship is not provided.


