Junior Data Scientist
Current-Own and maintain product to detect columns in provider data sheets-Distill and sifts through provider data to identify changes necessary to improve the quality of column detection-Created, maintain, and update a LLM model to detect correct columns-Improve the automation rate of the column detection pipeline from 75% to 95%-Utilize SQL databases to identify training set changes-Upload and connect LLM model to Veda's products via AWS-Frequently and accurately report my findings and their impact on our automation rate and product quality