Job Responsibilities: Conduct research and development on large multimodal models (LMMs) and AIGC generation algorithms, with a focus on image and video generation and editing, continuously advancing key algorithmic capabilities including but not limited to multimodal controllable generation, video continuation, image and video editing, and unified generation-and-understanding models; Explore and evaluate state-of-the-art video generation and unified generation–understanding models, closely tracking advances from both academia and industry in image, video, and multimodal large models, and incubate new capabilities, features, and application directions across device, cloud, and autonomous driving scenarios; Work closely with product, system, and engineering teams to continuously translate cutting-edge algorithmic innovations into deployable and deliverable product solutions, ensuring stable application of related technologies in real-world business scenarios. Job Requirements: Master’s degree or above in Computer Science, Artificial Intelligence, or related engineering fields (PhD preferred); 1–5 years of relevant research or development experience, with solid foundations in one or more of the following areas: image/video generation and editing, multimodal large models, unified generation-and-understanding models, reinforcement learning, etc.; First-author publications in top-tier conferences or journals are a strong plus, such as CVPR, ICCV, ECCV, NeurIPS, ACMMM, ACL, ICLR, etc.; Strong algorithm and deep learning model development skills, proficiency in Python / C++, and hands-on experience with mainstream AI frameworks such as PyTorch or TensorFlow, with the ability to independently conduct model design, training, and experimental analysis; Experience in image or video generation and editing algorithms is a plus; practical experience with large-scale visual data annotation, cleaning, and analysis is preferred; Broad technical vision with the ability to continuously follow and understand the lates...
