About

Sumit Saha is a passionate data scientist and machine learning engineer with a strong interest in building AI-driven products. With almost three years of relevant experience, Sumit has worked on several projects in the domains of NLP, information extraction, and model explainability. He is currently working as a Technical Writer at neptune.ai, where he is responsible for creating technical documentation and educating customers on how to use the product. Sumit's expertise lies in designing and engineering scalable AI pipelines and deploying them to production. He also has experience in training and tracking performance metrics for ML/DL models, interpreting models for contextual understanding and correctness, and maintaining and making improvements to the live product's codebase. In addition, Sumit is proficient in data wrangling, pre-processing, and EDA. He has also carried out relevant research work on industrial trends, methodologies, and algorithms. Sumit has worked as a Data Scientist - I and a Data Science Intern at SquadStack, where he developed robust data preprocessing and feature engineering strategies, trained ML algorithms, and evaluated models for interpretability/explainability using SHAP and LIME. He also developed a scraping engine to extract structured information from semi-structured data and learned about NLP and feature extraction using TFIDF, Word2Vec, etc. Sumit is proficient in Python, SQL, scikit-learn, scipy, statsmodels, tensorflow, xgboost, shap, matplotlib, pandas, and numpy. Sumit is passionate about the applications of AI for social good, especially in the domain of medicine and healthcare. He occasionally does some technical blogging too. Sumit holds a Bachelor of Technology degree in Computer Science and Engineering from Vellore Institute of Technology.