Work Experience

AI/ML Spectral Modeling Research

• Selected for a competitive, year-long AI/ML research assistantship focused on modeling noisy GQD spectral data to predict chromophore structures
• Research project integrates cyber twin protocols, TD-PiFCI+DFT spectral computation, and quantum modeling to enhance spectral prediction accuracy under real-world noise conditions.
• Contributed to data preprocessing, anomaly detection, and building predictive models using scikit-learn, Gaussian Process Regression, and Random Forests
• Participated in collaborative coding, weekly planning, and scientific documentation using tools like Python, NumPy, Pandas, and Matplotlib.