4+ Experience
Nearly 3 years of industry experience and 2 years of graduate student research assistant experience.
~ 30 Projects
Conducted nearly 30 projects across industry, research, and academic settings.
100K+ Lines of Code
Written and maintained 100K+ lines of code for production systems, ML/DL model development, deployment pipelines, rapid prototyping, and algorithm design.
About Me
I’m an Applied Data Scientist and AI professional with over 4+ years of experience across both corporate industry and academic environments.
My background includes hands-on experience in AI research and practical applications, such as developing real-time AI predictive services, building object detection systems, creating generative AI models, optimizing product designs, and enhancing quality performance through machine learning and deep learning techniques. Currently, pursing MSE in Data Science at Johns Hopkins University Whiting School of Engineering to specialize and advance my expertise. I’m a lifelong learner, passionate about applying advanced AI techniques to solve complex and real-world problems.
EXPERIENCE
Nearly 3 years of professional experience in the industry at Hankook Tire in South Korea, and two years of research assistant experience at CAI Research Lab, Hanyang University.
Hankook Tire
feb 2022 – jan 2025
AI-Engineer
Developed and deployed several AI models for production, including predictive maintenance and performance forecasting systems.
CAI Research Lab, Hanyang Univeristy
Sep 2019 – Aug 2021
Graduate Research Assistant
Led the development of real-time driver recognition systems for ADAS; conducted in-depth research and proposed novel methods in computer vision and deep learning.
Works/Project
Below is a selection of projects I’ve worked on across industry, research, and academic settings, focusing on AI-driven performance prediction, real-time computer vision, and LLM-based applications using machine learning and deep learning tools.
An intelligent real time driver activity recognition system using spatio-temporal feature
In this project a long-term recurrent convolutional network (LRCN) l is developed to detect up to nine various distracted driver activities includ-ing driving, drinking, texting, smoking, talking with rising hands, adjusting the navigation system, looking outside, nodding off to sleep, faint-ing inside a real vehicle cabin during the daytime and nighttime conditions.
Prompt Based Data Analysis and Visualization Chatbot APP
A prompt-based data analysis and visualization chatbot has been developed. The chatbot utilizes a large language model (LLM) to analyze data, create visualizations based on user requests, and display the results accordingly.
Hybrid Deep Learning Frame work for Distracted Driver Detection
In this project, we proposed a computationally efficient frame work that comprises a generative adversarial network (GAN) and convolutional neural network (CNN) framework for real time distracted driver detection during both day and nighttime conditions. The proposed system is composed of two consecutive steps.
Text-to-SQL AI Agent App
In this project, a Text-to-SQL chatbot powered by Google Gemini is developed. The chatbot allows users to input plain text queries and generate corresponding SQL query code, along with an example of the output and an explanation of the generated code.
Vehicle License Plate Detection Using YOLO Frame Work
This project implements a robust vehicle license plate detection system utilizing the YOLO (You Only Look Once) framework. The model is fine-tuned and leveraged to efficiently detect and localize license plates from vehicle images or video streams. The solution demonstrates high precision and speed, making it suitable for practical applications such as traffic monitoring, automated toll collection, and vehicle surveillance systems.
Contactless-Face-Mask-Recognition
In this project, a pretrained convolutional neural netwrok (CNN) is utilized for real time contactless face mask detection. The system effectively identifies faces with mask and non-mask regardless of the color of the mask. CNN is adopted to extract the meaningful features of the image input and perform the detection task.
Explore My Blog
Contact Me
Feel free to reach out with questions, collaboration ideas, or just to connect.
Get in touch with me