Staff Data Scientist
CurrentResearch Lead in ML, AI, and Automation for Entity Mapping, Specialist in Graph Representation Learning- Developed ML methods for mapping internet assets to entities (4x increase in average precision)- Drove application development using a several TB graph dataset (1011 nodes, 1011 edges)- Utilized Python and PySpark on AWS Sagemaker and AWS EMR clusters for feature extraction- Conducted non-linear feature engineering- Fit logistic regression, tree-based, neural network, and… Show more Research Lead in ML, AI, and Automation for Entity Mapping, Specialist in Graph Representation Learning- Developed ML methods for mapping internet assets to entities (4x increase in average precision)- Drove application development using a several TB graph dataset (1011 nodes, 1011 edges)- Utilized Python and PySpark on AWS Sagemaker and AWS EMR clusters for feature extraction- Conducted non-linear feature engineering- Fit logistic regression, tree-based, neural network, and graph neural network models to noisy data using scikit-learn, XGBoost, and Deep Graph Library (DGL)- Implemented the first ML inference model running in production at Bitsight using PMML- Investigated the application of graph representation learning for cybersecurity tasks- Led discussions and gave presentations to multidisciplinary teams and external stakeholders Show less