I worked at small to large-scale companies, so I enjoy getting my hands dirty and solving complex data-driven problems. My passion lies in enabling product growth using data and statistical theories.
End-to-End designing of company-wide product success measurement through constant hypothesis validation on user behaviors
Production-level software & data tooling development. Projects involve data pipelining, object-oriented design/refactoring, integration-testing, and operational maintenance.
Experience with petabyte-scale data handling techniques such as Spark
Familiarity with Ad-tech domains; real-time bidding, incrementality testing, brand-lift, AB experimenting, etc
End-to-End curated examples that show how to solve business problems using Amazon SageMaker and it's ML/DL algorithm. Mostly in Jupyter Notebook for easy accessibility