Developed high-fidelity Monte Carlo-based particle detector models using generative architectures like VAEs, GANs, and NFs, enhancing detection accuracy in the ATLAS experiment. Engineered and integrated software components for the ATLAS tagger system, improving data analysis workflows, and applied machine learning techniques in C++ and Python to collaborate with international teams. My work involved handling large-scale datasets, conducting end-to-end analysis, and contributing to research publications by simulating particle detector responses using generative models.

Developed machine learning algorithms for a graduate-level course at the National Superconducting Cyclotron Laboratory. Implemented supervised learning models to solve partial differential equations, enhancing quantum many-body simulations.Created interactive Jupyter Notebook modules for hands-on learning experiences and practical applications of ML concepts.

Performed calibration and developed statistical models for boron-doped charge-coupled devices to be used for neutron detection.

Performed numerical analysis of attenuation of fiber optic sensors under extreme neutron radiation.