GAYEON RUBY KIM

Recent Computer Systems Engineering graduate with hands-on experience in IT development, data analysis, and machine learning. Passionate about emerging technologies and how they enhance convenience and efficiency in everyday life. Strong problem-solving skills and a drive for innovation. Proficient in Python and Java, with a proven ability to apply advanced programming skills to real-world challenges. Eager to contribute to impactful IT projects and continue professional growth.

AWS Certified Data Engineer – Associate

Programming Languages:

• Python: Proficient in machine learning applications; experienced with Scikit-learn, PyTorch, and TensorFlow. Completed the Microsoft Student Accelerator data science module, applying Python for data analysis.
• Java: Developed a Blackjack game and a flight booking system, applying object-oriented and socket programming.
• C, C++: Additional experience in software development and system programming.

Project Management:

• Led and coordinated multiple university group projects, ensuring timely completion and effective collaboration.
• Used Jira for task delegation, progress tracking, and risk management.

Other Skills: Teamwork, Problem-solving

Emotional Talking Face Generation Project (03/2023 - 12/2023)

• Developed a DNN model in Python to generate a talking face video from an input image, text, and selected facial emotion, achieving a 17% performance improvement over previous work.
• Authored a paper based on this project, which was accepted at the Australasian Conference on Robotics and Automation (ACRA).

Mobile Autonomous Robot Project (07/2023 - 10/2023)

• Designed and implemented localisation and mapping solutions using Python, TurtleBot, and ROS in a Linux environment, applying SLAM techniques to enhance navigation in unknown environments.
• Utilised OpenCV for depth camera image processing, feature extraction, and visual enhancement, improving mapping accuracy and overall robot performance.

Traffic Sign Recognition and Operation Robot Development (09/2022 - 11/2022)

• Developed a Python-based machine learning model for real-time traffic sign recognition robot, achieving 85% accuracy.
• Collected, organised, and preprocessed a custom dataset, optimising model performance through hyperparameter tuning.

Handwriting Recognition Project (03/2022 - 05/2022)

• Implemented a DNN-based handwriting recognition tool in Python, achieving 75% accuracy on a dataset of 131,600 samples.
• Developed an interactive GUI to integrate machine learning results with real-time visual feedback, enhancing user engagement.