KPMG

Senior Data Scientist, Cybersecurity
2021-2022

• Developed and deployed machine learning regression models in Python to predict severity scores of ~150k vulnerabilities, effectively reducing the baseline mean squared error by 3.3 points
• Designed data model and dashboard for CISO risk product, coding in JavaScript, Python, and SQL to create a minimum viable product that earned over $1 million in funding
• Maintained data pipeline for a pharmaceutical manufacturer, aggregating data across pharmacies and re-sellers to detect grey market activity, saving more than $2.6 million by identifying false claims
• Created an AI Chatbot using Azure Bot Service to answer common cybersecurity questions from vendor representatives, exceeding test accuracy benchmarks by 9%

Data Scientist / Data Engineer
2019-2021

• Built natural language processing pipelines in Python and Spark for major financial institutions, creating contract management AI that surpassed human accuracy benchmarks for 100% of tasks
• Inspired a new machine learning-based approach that cut script development time by 75% and exceeded development expectations by 250%
• Designed and recommended big data architecture with a focus on disaster recovery and resiliency, offering real-time recovery and replication at the petabyte level
• Migrated critical infrastructure of a major bank's trading platform to the cloud, containerizing and deploying multiple services