Summary
Suman Adari is a data scientist and solutions architect with 8 years of experience and an MSCS in Machine Learning from Columbia University, currently applying advanced ML and MLOps practices at Explore Digits Inc. He has a strong track record of productionizing models—from recreating SAS procedures in Pandas/PySpark at scale to deploying Transformer and LSTM pipelines that achieved 94% precision across 50 ticket classes. Suman’s work in document extraction and lease abstraction combined computer vision with custom SpaCy NER to deliver >96–98% field extraction success across dozens of fields, and he has automated CI/CD model workflows with Jenkins and Flask. His research background in adversarial machine learning produced novel video-captioning attacks with near-100% success, demonstrating both deep theoretical insight and practical exploit development. Comfortable across cloud platforms and large databases (Oracle, Teradata, BigQuery) and fluent in PyTorch, TensorFlow, XGBoost and PySpark, he often bridges client-facing problem solving with low-level algorithm design. A less obvious strength is his ability to produce drop-in, 100% behavior-equivalent Python replacements for legacy SAS analytics, enabling large teams to migrate workflows without behavioral regressions.
8 years of coding experience
5 years of employment as a software developer
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at Columbia University in the City of New York
Bachelor of Science - BS, Computer Science, GPA: 3.8/4.0, Bachelor of Science - BS, Computer Science, GPA: 3.8/4.0 at University of Florida