Student Researcher - (Seed Model - Multimodal Interaction & World Model) – 2026 Start (PhD)

What you'll do

• Design and implement RL training systems for large-scale multimodal foundation models.
• Develop frameworks integrating video, audio, and language, with a focus on visual latent reasoning.
• Collaborate on evaluating models for world modeling, reasoning, and instruction-conditioned generation.

What they ask for

• Currently pursuing a PhD in Software Development, Computer Science, Computer Engineering, or a related technical discipline.
• Publications in accredited venues such as CVPR, ECCV, ICCV, NeurIPS, ICLR, or ICML, or other leading AI and ML conferences.
• Strong research background in at least one of reinforcement learning, multimodal learning, video understanding, or vision-language modeling.
• Must obtain and maintain work authorization in the United States; the company does not provide sponsorship or immigration-related benefits.

Nice to have

• Experience with RL in multimodal or interactive environments, video generation or diffusion-based generative models, or large-scale model training.
• Programming and engineering skills, including experience building ML training or evaluation pipelines.

Tools

reinforcement learning (RL), video, audio, language, diffusion-based generative models, distributed training, curriculum learning, memory-augmented transformers

AI focus

Develop multimodal foundation models and RL-based approaches for visual latent reasoning, bridging understanding and generation, and advancing multimodal assistant products.