Requirements: 1. Major in Machine Learning, Computer Vision, Computer Graphics, or related fields, currently pursuing a Master's degree or higher; 2. Proficient in deep learning frameworks such as PyTorch, with the ability to use programming languages like Python or C++; 3. Some project experience in image/video generation, familiar with frameworks such as Stable Diffusion, SVD, and DiT; 4. Familiar with Point Cloud and Occupancy data processing; 5. Knowledge of fine-tuning strategies for generative models like LoRA and ControlNet; 6. Prior experience in the autonomous driving field is preferred; 7. Publication in relevant top-tier conferences is a plus. Preferred Qualifications: 1. In-depth understanding of video generation work in the autonomous driving domain, including DriveDreamer, DriveArena, MagicDrive, and UniScenes; 2. Strong interest in technological innovation and self-learning abilities. 岗位要求： 1. 机器学习/计算机视觉/计算机图形学等相关专业，硕士及以上在读， 2. 熟练掌握 PyTorch等深度学习框架，能够使用 Python或 C++等编程语言； 3. 在图像生成/视频生成领域有一定项目基础，熟悉Stable Diffusion，SVD，DiT等生成框架； 4. 熟悉Point Cloud，Occ数据处理； 5. 熟悉LoRA，ControlNet等生成模型的finetune策略； 7. 对自动驾驶领域有相关项目经验者优先。 8. 有相关顶会论文者优先