Sahithi Vankayala

I’m a Data Engineer focused on designing data pipelines (ETL) and modeling data for analytics and machine learning use cases. I turn ambiguous, high-volume datasets into structured, query-ready schemas using structured thinking, reliable orchestration, and careful feature engineering.

During my Salesforce Developer Intern experience, I designed and deployed automation pipelines and schema customizations using Salesforce Flow, Apex triggers, and platform event handling. I supported deployment pipelines with Salesforce DevOps tools and documented system functionality to help analysts and cross-functional stakeholders move faster.

In my projects, I’ve built an Ad Analytics feature store and ETL pipeline that flattened semi-structured GA360 JSON into analytics-ready feature tables, including modeling high-cardinality fields and validating data integrity at each stage. I also built a real-time ETL pipeline with Python and Prefect, adding scheduling, retries, alerting, and structured logging to maintain production-style reliability with PostgreSQL.

For machine learning workflows, I engineered a 60-day transformer forecasting feature pipeline from AAPL data, created engineered financial signals, and benchmarked performance using RMSE and MAE against ARIMA. I enjoy collaborating with analysts and stakeholders to deliver dashboards and reporting views that make data usable and decision-ready.