World Model Research Intern (Generative AI)

About the role

Level Infinite, Tencent's global gaming brand, is hiring a World Model Research Intern (Generative AI Researcher) to focus on algorithm research and development for World Models and Video Diffusion Models, covering topics such as video generation and video interaction. The intern works alongside senior researchers on digital content generation and interactive agents.

Key responsibilities

• Data processing: assist with cleaning, filtering, annotation and preprocessing pipelines for large-scale video and image data to build high-quality training datasets.
• Model training: help build efficient training frameworks for diffusion models, optimize training workflows, and manage, monitor and fine-tune model training tasks.
• Technical innovation: take part in project discussions, propose improvements, and help integrate research findings into game video generation and virtual world construction scenarios.
• Frontier exploration: collaborate with senior researchers on new directions in digital content generation and interactive agents.

Required profile

• PhD or Master's student in Computer Vision, Computer Graphics, Machine Learning or a related field.
• Familiarity with generative models and a strong interest in applying generative AI to interactive entertainment and virtual world building.
• Good communication and collaboration skills.
• Publishing research in top AI and computer vision venues (CVPR, ICCV, ECCV, ICLR, ICML, NeurIPS) is a strong plus.

Required skills

• Strong background in deep learning with practical experience in image or video data processing.
• Ability to handle complex data cleaning and build robust data pipelines.
• Familiarity with mainstream video generation models; hands-on experience training or fine-tuning them is highly preferred.