About

Pradeep Nalabalapu is a highly experienced Machine Learning Engineer with over 18 years of relevant experience in the field. He is currently working as a Data Architect at deepiq, where he is responsible for designing software architecture for Data Science and Data Engineering pipelines. Pradeep has a strong technical background and is proficient in using PySpark, Tensorflow, and Scikit-learn. At deepiq, Pradeep has developed several PySpark modules that are part of the company's Data Studio product. He has also developed ML models to predict Oil resource density by location, using GeoTiff data. Additionally, he has implemented spatial indexes for boosting the speed of geo-spatial queries and achieved a 6X performance improvement over the existing Spark solution. Prior to deepiq, Pradeep worked as a Senior Machine Learning Engineer at mapr technologies, where he worked on an ETL solution for a retail client, Chicos. He also developed a machine learning deployment demo and an item-similarity-based recommendation engine, using Spark engine with Scala. Pradeep also trained a deep learning network for Speaker recognition on VoxCeleb dataset, using the SincNet network defined using Pytorch. Pradeep has also worked as a Consultant at clarity insights, where he was responsible for migrating an in-house data warehouse to AWS. He developed Spark Python programs for the Extraction and Transformation stages of ETL. Pradeep holds a BTech degree in Electrical Engineering from the Indian Institute of Technology, Madras, and an MS degree in Computer Engineering from Clemson University. He is proficient in various technologies such as ML, Spark, Scikit, Scala, Tensorflow, Pytorch, AWS, Java, and Data Warehouse. Pradeep is a seasoned Data Scientist, Senior Software Engineer, and has experience working on both the Frontend and Backend.