Responsibilities

We are seeking a research scientist/engineer to join our Multimodal Interaction & World Model team, dedicated to developing models with human‑level multimodal understanding and interaction capabilities and advancing multimodal assistants.

• Explore and research multimodal understanding, generative methods, machine learning, reinforcement learning, AIGC, computer vision, artificial intelligence, and other cutting‑edge technologies.
• Investigate the basic model of large‑scale/ultra‑large‑scale multimodal understanding and generation integration, conduct extreme system optimization; design data construction, instruction fine‑tuning, preference alignment, and model optimization; improve data synthesis, scalable oversight, reasoning and planning; build a comprehensive, objective, accurate evaluation system; and enhance large model capabilities.
• Advance the capabilities of multimodal models and world models, including multimodal...