Staff Data Scientist
Current• Created end-to-end Data Science and Machine Learning solutions using PySpark, SQL, and Python in Databricks environment.• Translated a legacy model from 200+ Databricks Notebooks to a modularized core of 3 and parallelized in Airflow to reduce run-time from 2 weeks to 2 days.• Developed Mentoring Program for budding Data Scientists which assisted them in a career change (several success stories).• Helped establish best practices for use of GitHub with Databricks, peer review process, ETLs, and ML model modularization.