Remote Lead Data Scientist
Current● Led code reviews as the automation lead for 12 direct report data scientists that enforced PEP8 coding standards with GitLab CICD pipelines.● Produced content filtering recommender systems for data driven decisions to show COVID19 impact data analysis on radio survey mailer returns due to USPS delays and redirected focus in sample selection to underperforming regions, increasing survey response rate by 100%.● Developed end to end production scale random forest classifiers to filter outliers with short branches of listening sample minutes that do not represent the overall quality of sample.● Translated Access, VBA, SAS and SQL code to Python to implement one click executions of processes to reduce production execution steps by 90%.● Centralized and templated custom Python libraries and images into dependency and container registries to support pip environments and Docker container pulls which enabled a minimum of 200 container builds per hour for over 200 employees in the data science department.● Modernized tech stack documentation from Word to Confluence and Jira for onboarding and training of new employees.● Collaborated with a multi-disciplinary team to stand up schemas and relevant tables for ingestion into the Hive data lake.● Served as the Tableau Server Administrator and SQL Server Database Administrator to troubleshoot production issues while improving visualization and query times.● Trained Generative AI models on Question2Answer open source forum to gain quick insights on tech stack questions posted by users. This allowed onboarding and knowledge transfer to increase by 100%.
