• Led a statistical analysis using data science techniques such as Machine Learning (ML), Multivariateanalysis (MVA), Gradient Boosted decisions Trees (GBDT), and Bayesian Updating, to extract signal from a very large dataset, with results produced in 2022.• Trained and optimized multiple Machine Learning (ML) classifiers to identify specific subsets of data using Gradient Boosted Decision Trees (GBDT).• Managed simulation/data using the SAM relational database management system and SAMweb for dataquerying.• Wrote production level code/scripts in C++, Python, and BASH, using SVN and Git for version control.• Implemented and optimized a Bayesian Updating technique to remove exogenous detector effects,allowing direct comparison between data and the model/theory.• Optimized selection criteria to curate a very large dataset, minimizing the total uncertainty on the finalmeasurement.• Tested NOvA’s production software on Amazon Web Services (AWS) and processed large datasets to verify our capabilities on the AWS platform using Python.• Worked in a large collaborative effort, around 300 people from all over the world: including India, Japan, UK, South America, Italy and more.• Presented talks at multiple conferences and meetings regarding the above work, including the AmericanPhysical Society national conference in April 2021.

Built a single photon counting experiment for use in testing quantum communication in a laboratorysetting.Simulated optical phase-frequency-space-time homography in Mathematica and published a paper on it.