World Model Research Intern - Game & Virtual Worlds

Tencent; Singapore; On-site; SGD 20,000 - 27,000; Part time

Job summary

Tencent is seeking a World Model Research Intern to focus on game world models, exploring video generation and interactive agents. You will join a research team and work on data processing, model training, and technical innovation in a fast-moving environment.

Ideal candidates are PhD or Master’s students in Computer Vision, Computer Graphics, or Machine Learning with deep learning experience, proficiency in processing image/video data, and a strong interest in applying generative AI to

Qualifications

• Enrolled as a PhD or Master’s student in Computer Vision, Computer Graphics, Machine Learning, or related field.
• Experience with deep learning and processing image/video data; data cleaning and pipelines.
• Interest in applying generative AI to interactive entertainment and virtual worlds.
• Strong communication and collaboration skills.

Responsibilities

• Assist in building an automated game data collection pipeline to capture precise internal states and construct a high-quality training dataset.
• Help build highly efficient training frameworks for diffusion models, optimize training workflows, and manage training tasks.
• Proactively propose innovative ideas and drive practical application of research findings into game video generation and virtual world construction scenarios.
• Collaborate with senior researchers to explore cutting-edge directions in digital content generation and interactive agents.

Skills

Deep learning

Generative models

Video data processing

Data pipelines

Communication skills

Education

PhD or Master’s student

CV/ML background

Job description

Tencent is seeking a World Model Research Intern to focus on game world models, exploring video generation and interactive agents. You will join a research team and work on data processing, model training, and technical innovation in a fast-moving environment.

Ideal candidates are PhD or Master’s students in Computer Vision, Computer Graphics, or Machine Learning with deep learning experience, proficiency in processing image/video data, and a strong interest in applying generative AI to