[Job Responsibilities]
1. Participate in the algorithm development and engineering implementation of visual and multimodal models;
2. Continuously follow up on the latest research in the visual/multimodal field and have excellent engineering and development abilities.
[Job Requirements]
1. Computer science or related field above master's degree, with solid computer vision foundation;
2. Proficient in PyTorch, in-depth understanding of computer vision models and Transformer architectures;
3. Familiar with mainstream visual/multimodal model technologies, and have practical application experience;
4. In computer vision or AI field, those who publish papers in top conferences/journals are preferred.
5. Have video understanding and other related research and development experience