Skip to content
View mkuangdotcom's full-sized avatar
🎱
🎱

Block or report mkuangdotcom

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
mkuangdotcom/README.md

Typing SVG

I am Ming Kuang, a Software Engineering undergraduate from UTM, Malaysia. I build intelligent, scalable systems from RAG pipelines and LLM agents to full-stack web and mobile apps.

  • πŸŽ“ B.Sc. Computer Science (Software Engineering) with Honours @ UTM | CGPA 3.98/4.0 | Dean's List every semester
  • 🌏 Spring Exchange @ University of Technology Sydney, Australia (2025)
  • πŸ€– Head of Department ML/AI @ Google Developer Groups on Campus UTM
  • πŸ‘¨πŸΌβ€πŸ’» 3Γ— intern β€” AI/ML Engineering Β· Data Engineering Β· Data Science
  • πŸ“… Seeking internship: Aug 2026 – Feb 2027
  • πŸ’¬ English Β· Mandarin Β· Malay Β· Hokkien

πŸ‘¨πŸΌβ€πŸ’» Work Experience

  • Dec 2025 – Mar 2026: AI/ML Engineer Intern @ Keysight Technologies
    • FastAPI + LangChain ReAct Agent + Azure OpenAI GPT-4 Β· RAG pipeline Β· LangGraph workflows
  • Apr 2025 – Jun 2025: Data Engineer Intern @ Undisclosed Hedge Fund, Singapore
    • ETL pipelines Β· PostgreSQL Β· gRPC Β· web crawlers Β· Docker
  • Jul 2024 – Oct 2024: Data Science Intern @ Money Match
    • Fraud detection ML (AUC-ROC 0.9) Β· Churn analysis Β· Reported to Bank Negara Malaysia

study Education

projects Projects

Artificial Intelligence & Machine Learning

  • mkuangdotcom/DualComm: Multilingual AI advocacy platform for migrant workers, supporting native dialects via WhatsApp and Telegram using RAG and speech-to-text
  • mkuangdotcom/Fraud_Detection: Neural network fraud detection model using SMOTE oversampling and Keras, achieving 93% accuracy on a highly imbalanced dataset
  • mkuangdotcom/Music_Recommendation_System: Music recommender using ALS collaborative filtering on 17.5M user-artist interactions, achieving 4.8x accuracy improvement over the popularity baseline
  • mkuangdotcom/Dream_Catcher: Sleep movement analyzer that tracks real-time head movements using OpenCV and MediaPipe
  • mkuangdotcom/AttendEase: Automated attendance system using facial recognition and computer vision

Full Stack Web

  • KIRAK26/FitTrackPro: Fitness and nutrition tracking platform built with ASP.NET Core Razor Pages, Entity Framework Core and LINQ
  • mkuangdotcom/Hotel_Project: Hotel management system with admin and user dashboards for booking and operations management, built with PHP and MySQL
  • mkuangdotcom/MedCare: Console-based hospital management system in C# .NET 8 with role-based access for patients, doctors, admins and receptionists, including appointment scheduling and email notifications

Mobile

  • tzee27/EduAlly: Flutter mobile app providing personalized support for students and teachers, with AI chatbot assistance and CCTV-based classroom analysis
  • mkuangdotcom/easyPKU: Medical appointment booking app built with Flutter and Firebase, featuring an integrated payment system
  • mkuangdotcom/AgriTrack: Cross-platform farm management app built with Flutter and Dart
  • mkuangdotcom/Weatherly: React Native weather app with real-time weather API integration
  • NickolasChen04/cropmaster: Farm intelligence platform using satellite data and AI for crop yield optimization

tools Things I Code With

Python C++ C# Java JavaScript R PHP HTML5 FastAPI .NET Django React Flutter LangChain Selenium pandas NumPy scikit-learn Keras OpenCV PostgreSQL MySQL Firebase Docker Git Azure

social Connect with Me

LinkedIn Email GitHub

Pinned Loading

  1. Fraud_Detection Fraud_Detection Public archive

    A machine learning project designed to detect and predict fraudulent transactions in a highly imbalanced dataset. The model uses techniques like SMOTE for class balancing and a Keras neural network…

    Jupyter Notebook 1

  2. easyPKU easyPKU Public

    A Flutter application for booking medical appointments, featuring Firebase backend integration and a payment system.

    Dart 2

  3. KIRAK26/FitTrackPro KIRAK26/FitTrackPro Public

    For .net a2

    C# 2

  4. Music_Recommendation_System Music_Recommendation_System Public

    Building a Music Recommendation System using User-Based Collaborative Filtering

    Jupyter Notebook

  5. DualComm DualComm Public

    [VHack 2026] DualComm is a multilingual AI advocacy platform designed to empower migrant workers to report workplace issues using WhatsApp and Telegram in their native dialects (such as Cantonese, …

    Python