About

Ananth Yarapathineni is a highly experienced IT professional with over 16 years of experience in building end-to-end data science projects using machine learning and deep learning technologies. He is skilled in architecting, developing, and implementing Big-Data enterprise software development initiatives and applications that perform large scale of Distributed Data Processing using Big Data ecosystem tools such as Hadoop, Spark (Java & Python), Hive, Pig, Sqoop, HBase, Oozie, MapReduce, YARN, and Kafka. Ananth has hands-on experience building machine learning and deep learning neural network models, from training to inference and deployment. He is proficient in Amazon Web Services (AWS) and can set up the cloud environment from scratch, build AWS infrastructure for data science projects and big data applications using AWS services like AWS EC2, Amazon Dynamo DB, Amazon Elasticsearch, Amazon S3, Amazon Redshift, AWS IoT Platform, AWS EMR, AWS SageMaker, AWS Kinesis Streams, AWS Lambda Functions, and also build and deploy machine learning or deep learning models using AWS SageMaker (training, hyperparameter tuning, and build and expose model as an endpoint). Ananth is skilled in designing and implementing micro-services based architecture for the deployment of models, deploying models on Kubernetes using Kubeflow workflows on AWS EKS, and building CI/CD pipelines, model deployment exposing endpoints as rest endpoints. He has also developed web and middleware technologies using servlets, JSP, Struts, spring, and enterprise technologies using EJB’s, web services, XML, X-path, XSLT, XSL, and Restful web services. Ananth has excellent skills in anomaly detection on univariate and multivariate time series data using machine learning algorithms. He is also proficient in developing and deploying forecasting models using statistical models, tree-based algorithms, and neural network deep learning algorithms. Ananth is skilled in analyzing, designing, planning, and implementing big data pipelines. He is also proficient in data preprocessing and feature engineering techniques using PySpark and Scikit learn preprocessing techniques. Ananth has excellent skills in improving processing speed or time reduction in Spark applications and improving Redshift query performance and optimization. He has worked with several companies in the past, including UST and Oracle, where he served as a Data Scientist & Big Data Architect and Principle Application Engineer, respectively. Ananth holds a Bachelor of Engineering in Electrical, Electronics and Communications Engineering from MD Sathak Engineering College and has completed his