Experience

Liberty Technology

• Cambodia
• Technology, Information and Internet

• Business Intelligence Analyst

  • Sep 2023 - Present

  Ho Chi Minh City, Vietnam



TAPTAP Vietnam

• Vietnam
• Technology, Information and Internet
• 1 - 100 Employee

• Data Scientist

  • Oct 2022 - Jul 2023

  Ho Chi Minh City, Vietnam – Implemented the use of Airflow, Spark, MongoDB, and Google Cloud to build a data storage and retrieval system for a personalized merchant in the application. – Architected a data management system utilizing Airflow, Spark, MongoDB, AWS and Google Cloud to build a data lake and data warehouse capable of transporting, storing and compartmentalizing more than 10 million transaction records. – Conducted a proof of concept to evaluate the performance of DataBricks in… Show more – Implemented the use of Airflow, Spark, MongoDB, and Google Cloud to build a data storage and retrieval system for a personalized merchant in the application. – Architected a data management system utilizing Airflow, Spark, MongoDB, AWS and Google Cloud to build a data lake and data warehouse capable of transporting, storing and compartmentalizing more than 10 million transaction records. – Conducted a proof of concept to evaluate the performance of DataBricks in architect- ing an experimental data lakehouse, involved testing and analyzing the capabilities of DataBricks in handling complex data processing tasks and integrating with various data storage systems. – Designed and implemented a recommendation system utilizing both collaborative filter- ing and content-based approaches to suggest preferred brands to a user base exceeding 3 million. – Constructed a dataset with five million records for a personalized merchant using Click- house Database and Superset SQL. – Created an intuitive and informative dashboard with various visualizations to help the merchant extract valuable insights into customer behavior and purchasing patterns. Show less



Information Systems Laboratory - VNUHCM - University of Information Technology

• Research Assistant

  • Jul 2020 - Aug 2022

  Responsibilities: Research on Visible Light Communication, Vehicle Communication and Sensing, and Optical Camera Communication; develop ideas, research and experimen- tally install state-of-the-art models for object detection, image classification, and regres- sion for artificial intelligence problems; organizing, planning experimental design and writing scientific articles using Latex and Python programming; presenting research results and reports to the supervisor.



Spring Knowledge Global Joint Stock Company

• Vietnam
• Information Technology & Services
• 1 - 100 Employee

• Fullstack Data Scientist

  • Apr 2021 - Oct 2021

  – Researched and built a solution for Vietnamese Document Understanding – Researched and developed a model to detect small objects like QR-code with more than 90% accuracy (mAP) using a state-of-the-art deep learning model – Deployed object detection model on Android app with 12FPS average using TensorFlow Lite and TensorFlow Edge TPU – Collected and built a dataset to train the model with more than 2000 images using the data augmentation technique



Officience

• Vietnam
• Outsourcing and Offshoring Consulting
• 200 - 300 Employee

• Machine Learning Engineer Intern

  • Aug 2020 - Oct 2020

  – Build an algorithm to optimize the data collection process and the process avoids crawl detection more than 50GB data from 5 real estate sites with a speed 15 times faster than the old algorithm over 4 hours by asynchronous programming – Performed Bash script that automatically inserts more than 50GB raw data into databases – Cleaned and wrangled more than 50GB of raw data on a database using the chunk data technique– Visualized large data in real-time using Matplotlib, Seaborn… Show more – Build an algorithm to optimize the data collection process and the process avoids crawl detection more than 50GB data from 5 real estate sites with a speed 15 times faster than the old algorithm over 4 hours by asynchronous programming – Performed Bash script that automatically inserts more than 50GB raw data into databases – Cleaned and wrangled more than 50GB of raw data on a database using the chunk data technique– Visualized large data in real-time using Matplotlib, Seaborn and PySpark Show less