About me

I am a Staff Research Scientist at the IBM Thomas J. Watson Research Center in Yorktown Heights, NY. I finished my PhD in Operations Research in the Department of Statistics and Operations Research at University of North Carolina at Chapel Hill in 2021 under supervision by Dr. Quoc Tran-Dinh.

Current Research

My current research focuses on Large Language Models (LLMs) for enterprise data management applications, particularly building end-to-end Text-to-SQL systems. I lead the development of NL2Insights, an automated pipeline that powers flagship IBM products including watsonx.data intelligence, BI Assistant, and Process Mining. Our system has generated over 200,000 SQL queries across 1,000+ databases at enterprise scale.

Recent Achievements

  • #1 on BIRD Leaderboard (2024): Led IBM Granite Text-to-SQL models to first place in both tracks of the prestigious BIRD benchmark, outperforming larger models like GPT-4 and GPT-4o
  • IBM Outstanding Technical Achievement Award (2025): For achieving first place on the BIRD leaderboard
  • IBM Growth Award (2025): For advancing Text2SQL service within watsonx.data intelligence
  • Multiple IBM Research Accomplishments (2024-2025): For NL2Insights product adoption and BIRD leaderboard success
  • Production Impact: Enabled multilingual Text2SQL capabilities across all IBM Cloud and AWS regions

I also continue research on stochastic optimization methods for machine learning, deep learning, and reinforcement learning.

Background

I come from Vietnam where I had my bachelor in Computer Engineering from Department of Computer Science and Engineering, Ho Chi Minh City University of Technology (Bach Khoa University). During my undergrad, I was a member of BKIT Hardware Club and participated in the Vietnam Robot Contest under BK4/BKIT Number One team in 2013.

My hobbies are travelling with my wife and exploring new places.

You can check out my CV here.