Experience

UVA Biocomplexity Institute

• United States
• Research Services
• 1 - 100 Employee

• Research Assistant - Computational Epidemiology

  • Aug 2021 - Present

  Charlottesville, Virginia, United States • Authored paper titled "Impact of Seeding and Spatial Heterogeneity on Metapopulation Disease Dynamics". • Accepted and presented at epiDAMIK an international workshop held in conjunction with ACM SIGKDD on data mining within field of epidemiology. • Summarized 22,000 plus disease simulations on a network based metapopulation model into a publicly sourced data set. • Introduced information entropy measurements into Covid-19 disease spread and peak analysis. • Constructed… Show more • Authored paper titled "Impact of Seeding and Spatial Heterogeneity on Metapopulation Disease Dynamics". • Accepted and presented at epiDAMIK an international workshop held in conjunction with ACM SIGKDD on data mining within field of epidemiology. • Summarized 22,000 plus disease simulations on a network based metapopulation model into a publicly sourced data set. • Introduced information entropy measurements into Covid-19 disease spread and peak analysis. • Constructed open-source web-app to simulate and produce interactive plots of disease spread within 223 countries and regions given disease characteristics.

• Network Science Intern

  • Jun 2021 - Aug 2021

  Charlottesville, Virginia, United States ▪ Developed software to automatically generate a tile grid map given shapefile data for a country. ▪ Collated literature to understand algorithms that were incorporated into the final product. ▪ Utilized network theory and optimization techniques to generate algorithms for any country or state. ▪ Software is utilized to display Covid-19 forecasts conveniently to policy makers.



Capital One

• United States
• Financial Services
• 700 & Above Employee

• Software Engineer Intern

  • Jun 2023 - Aug 2023

  McLean, Virginia, United States • Utilized Pyspark on EMR to extract training data into S3 for neural network to recommend data quality rules. • Leveraged information scraped from over 200,000 features found in Capital One datasets to train model to 93 percent accuracy. • Spearheaded data pre-processing with script to clean input data, applying schema validation and regex scraping for issue resolution. • Built pipeline for generation and validation of model input JSON from dataset ID, integrating Capital One Catalog… Show more • Utilized Pyspark on EMR to extract training data into S3 for neural network to recommend data quality rules. • Leveraged information scraped from over 200,000 features found in Capital One datasets to train model to 93 percent accuracy. • Spearheaded data pre-processing with script to clean input data, applying schema validation and regex scraping for issue resolution. • Built pipeline for generation and validation of model input JSON from dataset ID, integrating Capital One Catalog API information with statistical measures for features available on DynamoDB. Show less