The Seed Multimodal Interaction and World Model team is dedicated to developing models that boast human-level multimodal understanding and interaction capabilities. The team also aspires to advance the exploration and development of multimodal assistant products.
Responsibilities:
- Design and implement reinforcement learning (RL) training systems for large-scale multimodal foundation models
- Develop unified modeling frameworks that integrate video, audio, and language, with a focus on visual latent reasoning
- Explore RL-based approaches to bridge understanding and generation for multimodal visual reasoning
- Collaborate with researchers to evaluate models on tasks involving world modeling, reasoning, and instruction-conditioned generationMinimum Qualifications:
- 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, ICML, or other leading conferences in AI and ML
- Strong research background in at least one of the following: reinforcement learning, multimodal learning, video understanding, or vision-language modeling
Preferred Qualifications:
- Experience with reinforcement learning in multimodal or interactive environments
- Familiarity with video generation or diffusion-based generative models
- Experience with large-scale model training (e.g., distributed training, curriculum learning, or memory-augmented transformers)
- Solid programming and engineering skills, with experience building training or evaluation pipelines for ML models
As a condition of employment, all successful candidates must be able to establish authorization to work in the United States. For this position, the Company does not provide sponsorship or any immigration-related benefits.