Kishan Kumar Reddy Thamatam Venkata

Experience

• 

  Aegis Consulting Services

  Jun 2019 - Mar 2020

  Data/ML Engineer Intern

  - Analyzed, designed, and built modern data solutions using Azure PaaS services as well as assess the impact of new implementations on existing business processes under Team lead guidance.- Analyzed data from various marketing campaigns and customer interactions (web portal usage, email responses, public site interaction).- Performed incremental and full loads to transfer data from OLTP to Data Warehouse (Dedicated SQL Pool).- Use Azure Data Factory, Azure Synapse Analytics, T-SQL, Spark SQL, and U-SQL Azure Data Lake Analytics for ETL operations.- Ingested data into Azure Services (Azure Data Lake, Azure Storage, Azure SQL, Azure DW) and process it in Azure Databricks.- Automated pipeline runs in ADF and Azure Synapse Analytics through triggers (Scheduled, Tumbling Window, Storage Event).- Implemented pipelines in ADF for data extraction, transformation, and loading from various sources.- Responsible for estimating cluster size and monitor/troubleshoot Spark Databricks cluster.- Involved in the migration of data from on-premise SQL Server and file storage to Azure SQL Databases and storage accounts.- Responsible for data cleaning, feature scaling, and feature engineering using NumPy and Pandas in Python.- Conducted exploratory data analysis using Python Matplotlib and Seaborn to identify patterns and correlations between features.- Utilize feature selection methods (low variance, chi-squared, wrapper methods) to narrow down variables.- Develop various machine learning models using Pandas, NumPy, Matplotlib, Scikit-learn in Python (Ada Boosting, Gradient Boosting, etc).- Developed significant proficiency and practical skills in implementing and automating ETL and ELT workloads, utilizing a range of services including Azure Data Factory, Azure Synapse Analytics, Azure Databricks, and Azure Data Lake Storage Gen2. Additionally, gained hands-on experience in managing both supervised and unsupervised machine learning tasks. Show less