職缺描述
1. Research and develop generative AI technologies, focusing on image generation, cross-modal (vision, speech, text) integration technologies, and optimizing model performance and efficiency to support multi-platform applications. 2. Work on model optimization, including but not limited to techniques such as model compression, quantization, pruning, and knowledge distillation, to enhance AI model inference efficiency and reduce resource requirements. 3. Deploy generative AI models and multimodal AI models in real-world scenarios, ensuring that the models run efficiently across different platforms (e.g., mobile devices, embedded systems, cloud servers) and achieve real-time or near-real-time processing performance. 4. Participate in internal technical research groups (Study Groups) to exchange and discuss knowledge related to multimodal AI, model miniaturization technologies, and generative models.
收合內容