Responsibilities:
1.Responsible for research and development of image generation technologies, including the development of foundational models for text-to-image generation, image editing techniques, image enhancement, and multimodal generation of text and images.
2.Keep up with the latest advancements in AIGC algorithms, be responsible for the research and development and engineering implementation of related technologies, and accelerate the adoption and optimization of cutting-edge AIGC technologies in business scenarios such as live broadcasting, short video, and instant messaging.
Requirements:
1.A Master's or Doctoral degree in computer vision, pattern recognition, machine learning, or related fields.
2.Some work experience in computer vision, deep learning, machine learning, computer graphics, etc, familiar with mainstream models and algorithms, and capable of following up and implementing new algorithms.
3.Strong engineering implementation ability, proficient in at least one deep learning framework (such as TensorFlow, PyTorch, etc.).
4.Good learning ability, teamwork, and communication skills.
5.Priority will be given to candidates with experience in GAN-related image generation and editing, video editing, style transfer, portrait editing, etc.
6.Priority will be given to candidates with experience in Stable Diffusion, ControlNet, DreamBooth, LoRA, etc.
7.Priority will be given to candidates who have published papers in internationally renowned AI conferences or have won awards in ACM competitions.