Technical architect specializing in distributed systems and engineering leadership. I design infrastructure that handles millions of requests and build teams that deliver.
Currently Technical Manager at Gearment, building e-commerce infrastructure for the US market. Previously scaled Be Group's super-app platform to 25M+ users and led engineering teams at Geniebook.
Beyond my day job, I build products in fintech, gaming, and crypto. Active open source contributor with a research background in AI and computer vision.
Experience
Technical Manager · Gearment Inc.
A leading US-based print-on-demand and fulfillment company, processing millions of orders annually for e-commerce businesses worldwide.
Technical Lead · Geniebook
Singapore's leading AI-powered EdTech platform, serving 300K+ students across Southeast Asia with personalized learning experiences.
Software Engineer Lead · Be Group JSC
Vietnam's leading super-app ecosystem with 25M+ users, offering ride-hailing, delivery, fintech (Cake Digital Bank), and lifestyle services.
Backend Software Engineer · Teko Vietnam Technology JSC
Core technology arm of VNLife Group, building e-commerce, payment, and logistics solutions for Vietnam's largest retail ecosystem including Phong Vu and VNShop.
Software Engineer (Contract) · VNUHCM - University of Science - AI Lab
Research laboratory at Vietnam's top science university, bridging academic AI research with real-world applications in education technology.
Projects
Yuzu Money
Neobank and yield platform - earn interest on savings with competitive rates and seamless money management
Nova Service Loyalty App
Loyalty rewards app for Nova Service customers - earn points, redeem rewards, and track membership benefits
Pokerage
Online poker platform with real-time multiplayer gameplay, tournaments, and AI bots for practice matches
VSmart FaceID
Help optimizing the NCNN model size for mobile application
The New High-Performance Face Tracking System based on Detection-Tracking and Tracklet-Tracklet Association in Semi-Online Mode
Despite recent advances in multiple object tracking and pedestrian tracking, multiple-face tracking remains a challenging problem. In this work, the authors propose a framework to solve the problem in semi-online manner (the framework runs in real-time speed with two-second delay).