Lingfan Yu is a Senior Applied Scientist at Amazon, where he works on high-performance systems and infrastructure for large-scale AI workloads. He received his Ph.D. in Computer Science from New York University.
His research focuses on efficient training and inference of large language models and other emerging AI workloads on modern accelerators, including GPUs and specialized AI hardware. His interests span LLM serving, scheduling and batching, memory and KV-cache management, sparse and linear attention, parallelism, distributed communication, and hardware-software co-design. His research has been published in leading systems and machine learning venues, including SOSP, EuroSys, and MLSys.
Lingfan Yu is a Senior Applied Scientist at Amazon, where he works on high-performance systems and infrastructure for large-scale AI workloads. He received his Ph.D. in Computer Science from New York University.
His research focuses on efficient training and inference of large language models and other emerging AI workloads on modern accelerators, including GPUs and specialized AI hardware. His interests span LLM serving, scheduling and batching, memory and KV-cache management, sparse and linear attention, parallelism, distributed communication, and hardware-software co-design. His research has been published in leading systems and machine learning venues, including SOSP, EuroSys, and MLSys.