about
Hey there! I'm Nathan, a student at KAIST. I am immersed in the study of Business and Artificial Intelligence, complementing my strong foundation in algorithms and software engineering. As an Artificial Intelligence engineer, I channel my expertise into real-world projects, seamlessly blending theoretical knowledge with practical applications.
Outside of class, I actively engage in side projects, applying my skills to hands-on challenges. Feel free to reach out or explore my projects as I navigate the dynamic intersection of education and technology, leveraging my diverse experiences to discover the forefront of software engineering and artificial intelligence.
Welcome to my corner of the internet. I'm glad you're here!
experience
Dec – Aug 2024 I contributed to redesigning the company website to make it more intuitive and user-friendly. I also developed a chatbot to help users easily understand how to navigate the website, ask questions, and receive quick responses. Additionally, I transitioned the chatbot from a public service to an in-house solution, reducing costs while maintaining the service's effectiveness. I also assisted in deploying machine learning models.
- Web Development
- Machine Learning
- Security
Jan — July 2023 I undertook a research-driven project focused on engineering a modularized multiple-choice question-generating platform named KUIZ. This involved delving into the intricacies of Need-finding, Ideation, and Prototyping. Additionally, I played a role in conducting Usability Testing, ensuring that the developed platform not only met the research specifications but also aligned seamlessly with user expectations.
- HCI
- LLMs
Jan — Mar 2022 I worked on creating a dynamic dashboard to visualize information collected from test users' smartphones and smart bands. The aim was to effectively track and display their location and activities throughout the day, track anomalies, and provide insights into user behavior and trends.
- Data Visualization
- Data Analysis
Feb — Dec 2020 I worked on replicating a research paper that explored adversarial attack training using pretrained generative adversarial networks for photo applications. This involved a comprehensive study of the paper's methodology, implementation of pretraining models, and experimentation with adversarial attack strategies.
- Machine Learning
- Deep Learning
- GANs
projects
Artificial Neural Network (ANN) implemented from scratch to recognize handwritten digits from the MNIST dataset. The model is trained and evaluated for digit classification using a simple feedforward network.
- Python
- NumPy
- Machine Learning
A deep learning model using LSTM (Long Short-Term Memory) to classify IMDB movie reviews as positive or negative. The project explores sentiment analysis through sequence modeling.
- Python
- Keras
- TensorFlow
- Deep Learning
Predicts S&P 500 stock movements (up/down) using a Random Forest model to optimize trades. This project focuses on financial market prediction and optimization.
- Python
- Pandas
- Scikit-learn
- Machine Learning
An interactive machine learning visualization tool that allows users to explore different clustering and classification algorithms with real-time updates and visual outputs.
- Canvas
- Visualization
- Machine Learning
A browser extension for Youtube that enables the Picture-in-Picture (PiP) mode, allowing users to watch videos in a floating window while interacting with other tabs.
- TypeScript
- Browser Extensions
An online shopping platform that provides a secure and efficient e-commerce experience. It offers users an intuitive interface for browsing products, managing their cart, and making purchases.
- TypeScript
- MongoDB
- Express.js
- React
- Node.js
- GraphQL
- Firebase
- SCSS
The Pizza Menu API is designed to streamline the pizza ordering process.It ensures an efficient ordering experience for users. The API allows businesses to manage their pizza menus effectively and respond to customer orders promptly.
- Django Rest Framework
Ordering Pizza application that offers a convenient place to order pizzas online.
- JavaScript
- React
- SCSS
An Inventory Tracker that is a comprehensive solution for managing and tracking inventory. Developed with React Native, this application provides a seamless mobile experience for users to track their items.
- JavaScript
- React Native
The Django Blog project is a versatile and visually appealing blog platform. It offers users a seamless content creation, authentication, and publishing experience.
- Python
- Django
- Bootstrap
papers
2024 L@S'24 Workshop on Learnersourcing: Student-generated Content @ Scale
Hyoungwook Jin, Haesoo Kim, Nathan Mekuria Haile, Soyeong Min, Juho Kim
This paper presents a novel approach to learnersourcing multiple-choice questions by leveraging Large Language Model (LLM) interventions. The approach encourages modular, student-generated content at scale, facilitating more efficient and effective question creation in educational settings.
- Learnersourcing
- LLMs