Software engineer with strong experience in large-scale backend systems, data platforms, and machine learning. I have worked across the full lifecycle of ML-driven products — from data pipelines and model development to large-scale production systems. At Microsoft, I designed and built petabyte-scale real-time keyword recommendation services used across global markets, combining deterministic approaches with machine learning to drive measurable business impact. Currently at ByteDance, I work on core platforms for model compilation, training, and monitoring, improving system reliability, performance, and observability across large-scale ML pipelines. Previously at HTC DeepQ, I developed and deployed deep learning models for medical imaging into real-world clinical workflows, helping improve diagnostic efficiency and patient outcomes. I enjoy building scalable systems that bridge data, machine learning, and production engineering to solve real-world problems.