Background
Data scientist and systems engineer working at the intersection of statistical modeling, optimization, and real-world system deployment. First-class honors in Computer Science from Mahidol University; awarded a PhD fellowship in Operations Research at North Carolina State University, and a PhD fellowship at VISTEC's School of Information Science and Technology (IST). Research published in IEEE Access. The thread across all of it is mathematics and probabilistic modeling — the discipline of stating an economic question precisely enough that it has an answer.
Backend and data at scale
Career began in backend and data engineering at Agoda — building financial data pipelines, reconciliation systems, and distributed processing workflows on Kafka, Hadoop, and Spark. Years of operating financial infrastructure in production: high-reliability systems, complex business logic, and the discipline that comes from running money-handling pipelines that cannot drop a row. Backend engineering and scalable applications remain the foundation under everything that follows.
From financial models to decision systems
Transitioned into a data-science role at Siam Commercial Bank, focused on predictive modeling for financial products including mortgage refinancing strategies — applying statistical models to drive business decisions at scale. The pattern that carried through to DataGlass was already there: probabilistic models, financial outcomes, and real production systems.
DataGlass — research-grade modeling, deployed
Founder of DataGlass, the Decision Engine for e-commerce sellers. Unlike traditional analytics dashboards, DataGlass directly optimizes profit by deploying model-driven decisions across advertising, pricing, promotions, and inventory. The work centers on Bayesian modeling, causal inference, demand modeling under sparsity, and optimization under uncertainty — closed-loop systems where models do not only predict but execute and adapt decisions in real time.
Long-term focus
The direction is decision systems that operate reliably under uncertainty and produce measurable economic outcomes. The technical interest is Bayesian modeling, stochastic optimization, and robust systems, particularly in financial and marketplace environments. Beyond DataGlass, has led teams as a software engineer and engineering manager and founded multiple startups, including award-winning projects — but the long-term direction is a single one: mathematics and engineering, in production.