Nguyễn Hoàng Phương Trần is a PhD candidate at the University of Sydney, researching speculative decoding to improve the efficiency and responsiveness of large language model inference. His work explores algorithmic and system-level optimizations to accelerate generation while maintaining output quality.

Before commencing his PhD, Phương built extensive experience in industrial engineering, lean manufacturing, and logistics optimization, working on projects involving process improvement, supply chain performance indicators, and heuristic algorithms for operational efficiency in France.