Statistics • Software • Applied AI
My work sits at the intersection of data science, production software, and scientific decision-making. I’ve built statistical pipelines, internal lab-automation tools, and AI-assisted systems that support real-world teams.
I’m a data scientist who works at the intersection of statistics, software, and decision-making. My work at a seed-stage biotech company spans model research and development on one end and production automation and tooling on the other.
I completed a PhD in Bioengineering Data Science, where I learned to translate ambiguous problems into concrete solutions: production tools, metrics, evaluation frameworks, and actionable decisions.
I’m also drawn to the places where technical work meets business judgment. I’ve supported decisions in quantitative finance and venture capital (due diligence for a VC firm, pricing models at an investment bank). I hold a graduate certificate in technology entrepreneurship from UW, have worked at two early-stage startups, and coached at an entrepreneurship program for high schoolers.
Developing statistical, software, and applied AI systems for scientific decision-making in biotech.
PhD, Bioengineering Data Science. Graduate certificate in technology entrepreneurship, University of Washington.
Built a production statistical engine for proteomics screening from scratch, evaluating multiple modeling approaches and implementing fixes for p-value calibration and variance stability.
Replaced a manual, hours-long lab workflow with a backend-plus-Streamlit tool that reduced generation time to around two minutes and made the process self-serve for wet-lab staff.
Designed a rigorous retrospective study to assess whether an internal deep learning model added value over random selection, and used the results to prevent adoption of an unvalidated capability.
Architected an MCP-based internal tool that lets users query a large data corpus through natural-language chat, with an evaluation harness designed to validate tool-use behavior before release.
My PhD work reflects early technical training in computational biology and scientific modeling, while my current focus is on applied statistics, software, and real-world decision support.
A review of credibility standards in science, and how those ideas might apply to computational systems biology.
A Julia package for evolutionary algorithms applied to chemical reaction networks, including experiments with crossover and speciation.
A database of chemical reaction networks that oscillate, with an analysis of recurring structural patterns.