Senior AI Engineer building agentic, multimodal, and clinical AI systems
I am currently a Senior AI Engineer at Zoom, working on agentic workflows, LLM-based user simulation, and large-scale evaluation of automated systems. Previously, I was an Applied Researcher 2 at eBay Search Science, leading end-to-end development of multimodal product understanding and agentic search.
I drive end-to-end ownership of production AI systems, from problem formulation and model development to deployment, evaluation, and continuous iteration at scale. My work focuses on building reliable LLM and multimodal pipelines with rigorous evaluation and measurable product impact in cross-functional environments. In parallel, I develop interpretable EEG/iEEG models for epilepsy in clinical settings, and I am the main developer of PyHFO, an open-source platform for clinically grounded high-frequency oscillation analysis.
Across my research and applied work, I have authored 10+ first/co-first author publications and filed multiple U.S. patents.
VoidFormer: Mitigating Attention Distortion for Multimodal Learning Under Missing Modality
Jinglong Yang, Penghui Zhou, Yipeng Zhang, et al.
IEEE International Conference on Multimedia and Expo (ICME), 2026  
Coming Soon