Be responsible for the development and optimization of AIGC text/image/video generation algorithms, covering areas such as image generation, video generation, video editing, and video post - processing.
In view of the pain points in current AIGC algorithms, design and optimize the basic model framework and acceleration algorithms to improve training and generation speeds.
Based on the actual business scenario requirements, complete the design, training, and tuning of models, and rapidly promote the productization and implementation of the generative models in relevant scenarios.
Master's or doctoral degree in computer science, artificial intelligence, machine learning, applied mathematics, or related majors, with a solid foundation in computer graphics and artificial intelligence.
Possess strong engineering implementation capabilities, proficiently master programming languages such as Python and C++, and have experience in using deep - learning frameworks such as TensorFlow and PyTorch.
Have an academic background and R & D experience in video codec, image and video processing.
Have a solid research foundation in the fields of computer vision, machine learning, and deep learning, keep abreast of the latest technological advancements in the field, and be able to follow up, implement, and improve new algorithm capabilities.
Have good teamwork spirit and communication skills, be able to understand business requirements, and collaborate to complete project tasks.
Language proficiency in written and spoken English, Chinese, Cantonese, outstanding proficiency in written and spoken Putonghua