* Created a fully automated and scalable solution for file retrieval, data processing, and database insertion using the Amazon Cloud system AWS with Python and PostgreSQL. The data pipelines responded real-time to client-uploaded csv files and handled millions of data instances per day.
* Designed and implemented the Excel-formula Data Visualizer - a feature highly requested by major clients such as Pepsi and Suez Water - written in Python. The feature allowed users to query data while providing Excel-formula-styled input to customize the data visualization and was widely used by clients' data analyzers after feature roll out.
* Performed unit testing and built test cases for multiple internal machine learning tools powered by Python Scikit Learn package; achieved more than 80% test coverage.
* Responsible for the core product QA by performing UI testing and GraphQL API data retrieval validation; coordinated with the Front-end, Back-end, and Data Science team for feature implementation and maintenance.
* Conducted preliminary research for product feature development with the Data Science team, such as building the multi-variate anomaly detection function for water quality datasets.
* Performed data interpretation and visualization on large datasets for performance profiling of multiple Pepsi beverage plants;assisted sales team presentation
* Emagin is a product that brings AI solutions for water treatment and wastewater treatment operation.