I am an AI Engineer and an MPhil researcher in the School of Electrical Engineering, Computing and Mathematical Sciences at Curtin University. My research applies deep learning and materials informatics to hydrogen storage prediction in metal–organic frameworks (MOFs).

My research spans scientific data engineering, feature extraction, graph neural networks, model evaluation, interpretability, and high-throughput virtual screening. I build machine learning pipelines for experimentally synthesised and hypothetical MOFs to identify promising hydrogen-storage materials and translate model predictions into interpretable design insights — see my first-author paper in Applied Sciences.

Alongside my research, I work as an AI Engineer, developing reliable LLM applications, document automation, and knowledge retrieval solutions. Independently, I explore agent systems, tool orchestration, and open-source AI software — see Projects. My broader interests lie at the intersection of scientific AI and software engineering.

Research Interests

• Machine learning and deep learning for materials discovery
• Materials informatics and hydrogen storage in MOFs
• Graph neural networks and graph transformers
• Scientific data engineering and high-throughput virtual screening
• Model evaluation, interpretability, and robust AI
• Large language models, agent systems, and knowledge retrieval

Education

• Master of Philosophy, Curtin University, Perth, Australia, 2025 – present
• Master of Computing (Artificial Intelligence), Curtin University, Perth, Australia, 2024
  • Curtin Global Merit Scholarship
  • Dean of Engineering Commendation for Academic Achievement