Research Scientist in Multimodal Interaction and World Model - Seed - Graduates - 2027 Start (PhD)

Work on the Seed Multimodal Interaction and World Model team to build models for human-level multimodal understanding and interaction. Develop multimodal foundation models and world models for reasoning, planning, and interaction. Create training pipelines with data curation, alignment, and reinforcement learning, and enhance agent capabilities like perception, memory, and tool use. Explore next-generation interaction paradigms between humans and intelligent systems.