With over 10 years of in-depth experience in the field of AI model & infrastructure, I have accumulated full-link practical expertise spanning from AI-on-chip algorithm hardware adaptation, participation in high-performance AI chip research and development, to building efficient and scalable AI infrastructure. Currently, I am focusing on AI performance optimization at Volcano Engine, working to break through bottlenecks through synergy among models, algorithms, chips, and infrastructure, and continuously empowering efficient AI services.