Software Developer
& Data Science Enthusiast

Building at the intersection of software & data science

MS Data Science student at UC San Diego (GPA 3.77) with 2.5 years of industry experience at IBM, promoted from intern to Software Developer. I like figuring out why something is not working for someone, then rebuilding it in a way that holds.

At IBM I rebuilt a data validation pipeline that was silently failing and taking down batch jobs with it - processing time dropped 90%. I built an LLM-based router that analysed code diffs to decide which cloud environments actually needed testing, cutting redundant CI/CD runs and saving 40% in compute costs. I also ran clustering and time-series analysis on multi-cloud usage logs to surface waste patterns for stakeholders.

At Samsung Prism I built a pipeline to generate phoneme data from 10,000+ contact names using the CMU Pronouncing Dictionary. The 10% gain in recognition accuracy fed directly into the next model iteration.

Currently working part-time as a Student Build and Release Engineer at UCSD IT Services, keeping CI/CD running for campus engineering services.