Senior Researcher - Video Generation

About the role

Tencent's Technology Engineering Group (TEG) is recruiting a Senior Researcher for video generation. The role focuses on research and development of large-scale video world models, from dataset design and model architecture to pipeline optimization and evaluation.

Key responsibilities

• Engage in R&D of large-scale video world models, including designing and building training datasets, designing foundational model architectures, optimizing pre-training, SFT and RL pipelines, evaluating model capabilities and exploring downstream applications.
• Analyse R&D challenges scientifically, identify performance bottlenecks and derive solutions from first principles to speed up model development and iteration.
• Explore alternative paradigms for world models and investigate next-generation architectures.

Required profile

• Bachelor's degree or higher (preferred) in Computer Science, AI, Mathematics or a related field, full-time education required.
• Solid foundation in deep learning algorithms and hands-on experience in large model R&D; experience with diffusion and autoregressive models is highly preferred.
• Publications in top-tier venues and practical experience in text-to-image/video generation are strong pluses.
• Exceptional candidates with ACM-ICPC or NOIP competition experience will be given top priority.

Required skills

• Proficiency in the implementation details of deep learning networks and operators.
• Experience in training and inference optimization, CPU/GPU acceleration and distributed training and inference acceleration.
• Strong learning agility, communication skills, teamwork and curiosity.