Bio

Full stack data scientist with at least 3 years experience in deploying machine learning features to over thousands of customers and communicating insights to stakeholders. I enjoy dabbling in side projects such as open source contribution. I've worked in projects related to hypothesis testing, recommender systems, classification, regression, clustering, ensemble methods, anomaly detection, time series forecasting, topic modelling, deep neural networks and their applications for natural language processing and signal processing. I also have practical skills in software development and object oriented programming. Libraries: tensorflow/keras, scikitlearn, pyspark, pandas, pytest, statsmodel Tools: Data Visualization (Tableau), SQL (Teradata, Postgres, Hive), conda/virtualenv, MLFlow MLOps: Azure DevOps, Docker, Shell Scripting, Flask Platforms: Azure, Databricks, GCP (app engine, pub/sub)