Job Responsibilities:
- for research and development on the algorithm for Large Vision-Language Generation Models in the multimedia field, make breakthroughs in key algorithm technologies, such as controllable image generation, fine-grained generation content control, text-to-image generation, text-to-video generation, image editing, object addition & removal & alteration in images, etc.
- explore the latest technologies in large vision-language model, deeply understand the technological development trends in the multimedia field such as multimodal large model generation and editing, as well as industries like mobile phone / autonomous driving, to incubate new products and features.
- with relevant product teams to ensure the smooth delivery of related products.
Job Requirements:
- degree or above in Computer Science, Artificial Intelligence, or related engineering fields (Ph.D. preferred).
- background in large vision-language model, AIGC, image processing, and machine learning technologies, with 1-5 years of relevant industry experience. Priority will be given to those who have published papers in relevant academic conferences and journals as the first author, such as CVPR, ICCV, ECCV, NeurIPS, AAAI, ACMMM, ACL, ICLR, ACL, etc.
- algorithm and deep learning model development skills, proficient in Python/C++ and relevant AI development frameworks such as TensorFlow/PyTorch.
- in image/video processing algorithms or the development of image processing chips.
- vision, able to stay informed about the current status and trends in academia and industry
- independent thinking ability and teamwork spirit.
Next Step
Click “apply” or send resume to: Ryce [email protected]
EA Licence No.91C2918| Personnel Registration No. R23117258
