About

Varnit Agnihotri is a highly experienced Senior Data Scientist at LinkedIn with over 11 years of relevant experience in building large scale, distributed software and machine learning systems. He is an expert in data science, research science, ML, software engineering, and Spark. Currently, Varnit is working at LinkedIn, where he is responsible for understanding and fighting spam. He is leveraging his expertise in machine learning to develop and implement cutting-edge algorithms that can detect and prevent spam on the platform. Prior to LinkedIn, Varnit worked at Amazon in various roles. As an SDE-II in the Machine Learning Group, he was responsible for building machine learning models for website classification and category identification. He also worked on end-to-end model building for identifying websites for lead generation and designed and implemented an entire system for data collection, model building, model deployment, feature engineering, and predictions. Additionally, he prototyped and developed several models for figuring out correct fit-sizes for Amazon customers and improved legacy systems by increasing performance and replacing rule-based systems with machine learning models. In another role as an SDE-II at Junglee.com, Varnit built a log analysis platform and pipeline for the Junglee Selection platform. He also designed and implemented fault-tolerant and book-keeping pieces of a large-scale crawling platform responsible for millions of crawls per day on thousands of targeted websites. Varnit holds a Bachelor of Technology (B.Tech.) in Computer Science from the Indian Institute of Technology (Banaras Hindu University), Varanasi, where he graduated in 2011. Overall, Varnit is a highly skilled and experienced data scientist with a proven track record of building large scale, distributed software and machine learning systems. His expertise in data science, research science, ML, software engineering, and Spark make him a valuable asset to any organization looking to leverage machine learning to solve complex problems.