At IBM, I built Snowflake and PySpark ELT pipelines for Blue Cross of Idaho, consolidating member, provider, and claims data into a centralized MDM platform. I also developed automated email parsing for HaloMD, extracting 24 structured fields at 94% accuracy and reducing manual review by 71%.
I've led SQL analysis teams in Databricks and built scalable PySpark pipelines processing 1M+ retail transactions. My work combines data quality, modeling, machine learning, and clear stakeholder reporting.
