Boris Kundu
About Boris Kundu
Boris Kundu is a Machine Learning Engineer at Cohere Health in Boston, Massachusetts, where he has worked since 2022. He specializes in creating custom applications for medical services that utilize machine learning for critical predictions and automated decision-making.
Work at Cohere Health
Boris Kundu has been employed as a Machine Learning Engineer at Cohere Health since 2022. In this role, he focuses on creating custom applications that facilitate critical predictions and automate decision-making within medical services. His work involves integrating machine learning models into web-scale services, which support downstream rule execution. This position is based in Boston, Massachusetts, United States.
Education and Expertise
Boris Kundu holds a Bachelor of Engineering in Information Technology from Netaji Subhas Institute of Technology, where he studied from 2005 to 2009. He further advanced his education by obtaining a Master of Engineering in Artificial Intelligence from the University of Cincinnati, completing the program from 2021 to 2022. His educational background provides a strong foundation for his expertise in machine learning and artificial intelligence applications.
Professional Background
Boris Kundu's professional journey includes significant roles at various organizations. He began his career at Bharat Heavy Electricals Limited as a Developer in 2007 and 2008. He then worked at Amdocs for nine years, holding positions as Software Development Team Lead and Software Developer from 2009 to 2018, and later as Solution Designer and Product Owner from 2019 to 2021. He also contributed to machine learning projects at the University of Cincinnati from 2021 to 2022.
Achievements in Machine Learning
During his tenure at the University of Cincinnati, Boris Kundu developed advanced statistical models utilizing embeddings and deep learning techniques for document processing in clinical settings. This work led to significant cost savings and efficiency improvements. At Amdocs, he transformed unstructured clinical text for machine learning purposes, optimizing service request ranking and achieving a 90% auto-approval rating, which resulted in substantial monthly savings.