I'm Wentao Huang, and I recently received my Ph.D. in Computer Science from the National University of Singapore, where I was advised by Prof. Kian-Lee Tan and collaborated with Prof. Bingsheng He.

My research applies systems-level optimization and performance modeling to accelerate AI and large-scale data processing on emerging hardware, including CXL, NVMe, and GPUs. I am especially interested in building high-performance agentic systems and efficient mixture-of-experts (MoE) LLM inference engines. I am currently exploring research and engineering opportunities, and welcome conversations about research collaborations.

Find more about me on my personal homepage or get in touch.