$whoami
Vaikunth Desai
$role
Data engineer building governed, reliable pipelines for regulated financial data — masking, Unity Catalog governance, and PySpark performance on Azure Databricks.
$open-to
Data engineer roles in New York (open to relocate)
#about
I move sensitive financial data safely and fast. At KPMG I build masking and governance into Azure Databricks pipelines, standardize metrics with Unity Catalog, and tune PySpark jobs to scale from months to years of data. Before that I built anomaly-detection and forecasting models at Capital One. I hold an M.S. in Statistics, and I care most about pipelines that are correct, tested, and easy to trust.
#stack
languages
cloud & data
engineering
ml & bi
currently deepening
#projects
Real-time browser extension that summarizes professional posts using OpenAI, backed by a serverless AWS backend, local storage, and an interactive UI.
Retention models and automated profitability dashboards that surface where product-segment margins can be improved.
Regression models forecasting regional sales across 50+ locations, with predictions integrated into Excel-based planning tools.
#publications
Research on Big DataIJCA ↗ COVID detection using CNNsIJCA ↗#contact
Based in Houston, TX. Open to data engineer roles in New York and remote. The fastest way to reach me is email.