Job Description

About the team
Welcome to the Multimodal Interaction & World Model team. Our mission is to solve the challenge of multimodal intelligence、virtual reality world interaction in AI. We conduct cutting-edge research on areas such as Foundations and applications of multimodal understanding models, Multimodal agent and inference, Unified models for generation and understanding, World Model. Our team is comprising experienced research scientists and engineers who are 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. We foster a feedback-driven environment to continuously enhance our foundation technologies. Come join us in shaping the future of AI and transforming the product experience for users worldwide.

As a project intern, you will have the opportunity to engage in impactful short-term projects that provide you with a glimpse of professional real-world experience. You will gain practical skills through on-the-job learning in a fast-paced work environment and develop a deeper understanding of your career interests.

Applications will be reviewed on a rolling basis - we encourage you to apply early.
Successful candidates must be able to commit to at least 3 months long internship period.

Responsibilities
- Explore and research multi-modal understanding, generative, machine learning, reinforcement learning, AIGC, computer vision, artificial intelligence and other cutting-edge technologies.
- Explore the basic model of large-scale/ultra-large-scale multi-modal understanding and generation interweaving, and carry out extreme system optimization; Data construction, instruction fine-tuning, preference alignment, model optimization; Improve the ability of data synthesis, scalable oversight, model reasoning and planning, build a comprehensive, objective and accurate evaluation system, and explore and improve the ability of large models.
- Explore and break through the advanced capabilities of multi-modal models and world models, including but not limited to multi-modal RAG, visual COT and Agent, and build a universal multi-modal Agent for GUI/ games and other virtual worlds.
- Use pre-training, simulation and other technologies to model various environments in the virtual/real world, provide the basic ability of multi-modal interactive exploration, promote application landing, and develop new technologies and new products with artificial intelligence technology as the core.