Lavanya Reddy

I've designed end-to-end ETL pipelines in Azure Data Factory that load data from multiple source systems into Azure SQL. I automated scheduled runs and monitoring checkpoints to identify failures early and keep downstream data reliable.

For a retail data warehouse project, I designed a star schema, built SQL transformations for fact and dimension tables, and connected Power BI for scalable reporting. I also tuned indexes and validated query performance on large tables to reduce dashboard load times.

I've built data-to-model workflows using Python, Pandas, and Scikit-learn, including a customer churn pipeline for 7,043 records that achieved 78.46% accuracy with a Random Forest classifier. My work includes data quality validation, feature engineering, and detecting schema drift before model handoff.

Through my AI internship at iStudio Technologies and Deloitte's Data Analytics Job Simulation, I've worked across data preparation, machine learning, transformation, and reporting workflows. I'm looking to build reliable, scalable infrastructure as part of a Data Engineering team.