About
I build data systems for market surveillance and regulatory workflows.
Building regulatory data pipelines and surveillance systems with Python, PySpark, Hive, and machine-learning methods to improve speed, accuracy, and reusability across market workflows.
I work on Python, PySpark, and Hive systems that turn complex regulatory data into practical engineering workflows.
My work includes modernizing legacy surveillance logic, building reusable data pipelines, and applying statistical and machine-learning methods to improve the precision of alerting workflows.
Current focus
- Scalable regulatory data pipelines across market domains.
- Maintainable Python implementations of surveillance logic.
- More precise alerting through statistical and machine-learning methods.