Proficient in end-to-end machine learning workflows, including data preprocessing, feature engineering, model training, and evaluation. Experienced with Python-based data science tools such as Pandas, NumPy, Scikit-learn, and PyTorch, with strong visualization skills using Matplotlib and Seaborn. Skilled in exploratory data analysis and predictive modeling, especially using Graph Neural Networks for complex structures. Comfortable working in Jupyter Notebook within the Anaconda environment and familiar with R, Tableau, and PostgreSQL for statistical analysis and dashboard reporting.
Projects
Deep Learning for Hydrogen Storage Prediction in MOFs
Developed a deep learning framework to predict hydrogen storage performance in MOFs by integrating structural and chemical features. Designed and evaluated multiple neural network architectures and implemented a multi-task learning strategy to measure storage metrics across conditions. Surfaced high-performing materials and structure–property insights to guide data-driven discovery for clean energy applications.
Project 2
In Progress...
Skills
Python
Pandas
NumPy
Scikit-learn
PyTorch
Feature Engineering
Model Evaluation
Predictive Modeling
GNN
Data Analysis
Matplotlib
Seaborn
Jupyter Notebook
R
Tableau
PostgreSQL
JIRA
Git
Education
02/2025 – Present
Curtin University – Master of Philosophy (Computing)
02/2024 – 12/2024
Curtin University – Master of Computing (Artificial Intelligence)
02/2023 – 12/2023
Curtin College – Masters Qualifying Program
