Software Engineering Intern & CS Candidate

Javy Aguinaldo

619-***-**** **************@*****.***

Education

University of California San Diego San Diego, CA

Bachelor of Science - Computer Science Graduated June 2026 El Capitan High School San Diego, CA

Graduated with Honors Graduated June 2022

Relevant Coursework

• Data Structures • Operating Systems • Computer Architecture • Parallel Computing

• Machine Learning • Software Engineering • Cryptography • Recommender Systems Experience

Tractor Supply Company Team Member August 2024 – June 2026 Tractor Supply Company San Diego, CA

• Delivered customer service by assisting 50+ customers per shift, resolving questions and identifying solutions.

• Operated point-of-sale systems while handling cash and transactions with accuracy and attention to detail.

• Maintained organized inventory and sales floor presentation by following company procedures and standards.

• Adapted quickly to changing priorities and supported different departments as business needs required. Projects

World War Interactive Learning Game TypeScript, Konva.js September 2022 – December 2022

• Collaborated in a 4-person team to develop an interactive educational by designing a controller-based architecture in TypeScript using Konva.js to manage multiple gameplay modes, learning modules, and mini-games

• Implemented a centralized screen-switching system that managed 20+ UI views, including dialogue, interactive maps, zoomable learning screens, and game stages.

• Designed a modular controller-based architecture that separated navigation from gameplay logic, improving scalability and simplifying future feature additions Food.com Recipe Rating Prediction Python, Pandas, NumPy September 2024 – December 2024

• Developed a recommendation system that predicted user ratings for 680K+ recipe interactions using the Food.com Recipe and Review dataset, enabling comparison of collaborative filtering approaches.

• Implemented and evaluated multiple recommendation models, including global mean, item mean, user-item bias, and matrix factorization, using Mean Squared Error (MSE) as the evaluation metric.

• Improved validation performance by 11.3%, reducing MSE from 0.8326 (baseline) to 0.7385 with a user-item bias collaborative filtering model.

Technical Skills

Languages: Java, C/C++, Python, TypeScript, JavaScript, PowerShell, VBA Frameworks: Node.js, PyTorch, Konva.js

Developer Tools: Git, Docker, VS Code, Microsoft Excel, Microsoft Word Libraries: pandas, NumPy, Matplotlib