I build AI systems and data workflows for reliable applications and rigorous research.
AI systems, research methods, and the workflows that connect them.
Product Lead & AI Engineer
Research platform
Built conversational practice, study onboarding, and researcher review tools for a UT Austin parenting study.
Data Harmonization & Survey Analysis
Manuscript in preparation
Harmonized NHIS survey data across more than two decades, with reproducible SAS pipelines and documented quality checks.
Creator & Lead Developer
Public methods platform
Built a research-methods site and citation-verification skill that cross-checks references against scholarly databases.
Jun 2025 – Jul 2026
Built survey-harmonization and analytics workflows for NHIS health-inequality research, with reproducible SAS pipelines, cross-tab verification, drift checks, and missingness diagnostics.
NHIS case study →Aug 2024 – May 2026
Co-founded a cross-school community at UT Austin and organized workshops, speaker events, and practical AI learning material.
Jun 2024 – May 2025
Taught SPSS and R labs for a two-semester doctoral quantitative-methods sequence (Quantitative Data Analysis I and II), covering ANOVA, regression with mediation and moderation, missing data and multiple imputation, factor analysis, and structural equation modeling. Designed a 12-week online statistics preparatory course for incoming PhD students and provided program-level analytic support.
Jun 2022 – May 2023
Built customer-lifetime-value models and segmentation frameworks for wealth-management campaigns using cohort analysis and QC-validated data pipelines, lifting high-net-worth client conversion by 20%. Developed Tableau dashboards that cut marketing decision cycle time from 7 days to 4.
Nov 2021 – May 2023
Led a SQL and CRM migration that deduplicated 12,000+ records and implemented a 15-dimension customer taxonomy for downstream reporting. Redesigned outreach segmentation analytics for continuing-education programs, raising survey response rates from 8% to 48% over successive campaigns.
I design and run rigorous quantitative analyses: causal inference, multilevel and complex survey models, and inequality metrics, with reproducible pipelines and documented assumptions.
I build reproducible data workflows across Python, R, and SAS, with version control and clear documentation from raw data to analysis-ready outputs.
I design LLM applications and context systems with evaluation, safety guardrails, and human-in-the-loop review, focused on reliability rather than demos.
I translate research requirements into study operations and AI tools, from Qualtrics consent flows to PMTO-informed evaluation of conversational systems.
Focus on Artificial Intelligence and Data Science. Coursework included Machine Learning, Explainable AI, AI in Health, Responsible Data Management, Data Wrangling, and Prompt Engineering.
Honors: Academic Excellence Award, College of Business Leadership Award, Business Honors Program, and Dean's List.
Research contributions span study platforms, survey harmonization, and reproducible analysis. Acceptance and review status are shown for each contribution.
BRAT platform contribution · Intersectionality analysis · NHIS methods
These are the kinds of questions I keep coming back to in my work.
I built a custom GPT around Stanford's Designing Your Life method. It is not a career test and it will not hand you a life plan. It guides a reflective conversation to help you see where you are, find the real problem, imagine several futures, and turn them into small, low-risk experiments. English and Chinese versions, plus the full system prompt.
Deep research agents write literature reviews fast. Then you click the citations, and the real work starts.
One study found AI disclosure in about 0.1% of a 75,000-paper subset. What can that narrow measure tell us about research transparency?
I'm always happy to talk about AI in health, research workflows, or weird data problems.
If you're working on something in that space, I'd love to hear about it.