Research Scientist (Seed Model - Multimodal Interaction & World Model)

What you'll do

• Develop large-scale multimodal foundation models and unified video, audio, and language modeling frameworks.
• Explore reinforcement learning methods connecting multimodal understanding and generation for visual reasoning.
• Collaborate on evaluating models for world modeling, reasoning, and instruction-conditioned generation.

What they ask for

• Completing or recently completed an MS in a listed or related discipline.
• Publications in accredited venues, such as CVPR, ECCV, ICCV, NeurIPS, ICLR, or ICML.
• Strong research background in at least one of reinforcement learning, multimodal learning, video understanding, or vision-language modeling.

Nice to have

• Completing or recently completed a PhD in a listed or related discipline.
• Experience with multimodal or interactive-environment reinforcement learning, video generation or diffusion models, large-scale training, or ML training/evaluation pipelines.

Tools

Reinforcement Learning

AI focus

Research and develop multimodal foundation models, visual latent reasoning, and reinforcement learning approaches for multimodal understanding, generation, and interaction.