多模态世界模型算法研究员/专家-Seed
Core
Researching and optimizing large-scale multimodal foundation models, world models, and generative AI systems for virtual and real-world environments.
Role type
Senior Research Scientist / Expert in Multimodal World Models
Builds
Multimodal agents for GUI/games, scalable oversight systems, and AI-driven virtual/real-world modeling
Domain
Artificial Intelligence, Multimodal Learning, Generative AI, Computer Vision
Deliverable
production ML models
Required skills
Multimodal understanding, Generative AI, Reinforcement Learning, Computer Vision, Large Language Models, Model Optimization, Data Synthesis, Scalable Oversight, Model Reasoning, Planning
Preferred skills
Publications in top-tier conferences (CVPR, NeurIPS, etc.), Competitive programming awards, Leading high-impact projects in world models or rendering
Technologies
C/C++, Python, Pre-training, Simulation
Responsibilities
Explore frontier technologies in multimodal understanding and generation; Optimize large-scale multimodal foundation models; Build evaluation systems and improve model reasoning/planning capabilities; Develop multimodal agents for virtual environments; Model virtual/real-world environments using pre-training and simulation.
