Experience
From applied mathematics to computational medicine, with education, research, and industry along the way.
Education
Northeastern University
Interdisciplinary Ph.D. in Computational Medicine · ABD · GPA 4.0/4.0
- Passed the Ph.D. candidacy exam in Aug 2025; passed the dissertation proposal defense in Jun 2026 — now all-but-dissertation (ABD), expected to graduate in June 2027.
- Research focus: multimodal clinical data (EHR, medical imaging, clinical notes, wearable data), large language models, and precision medicine.
University of Pennsylvania
M.S. in Social Policy & Data Analytics · GPA 3.86/4.0
2021–2022 scholarship recipient; advisor: Dr. Li Shen. Graduate researcher at Shen Lab, DBEI & PennAITech, Perelman School of Medicine.
Nanjing University of Finance & Economics
B.S. in Mathematics & Applied Mathematics
Research & Work
Graduate Researcher
Shen Lab, Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania
- Led 5 interdisciplinary AI research projects on LLM fine-tuning, evaluation frameworks, and healthcare applications — spanning disease detection, trustworthy AI, and fairness-aware medical database analysis.
- Developed MentalGPT, a system of LLMs fine-tuned on MentalChat16K, outperforming base models and baselines on 7 mental-health metrics, evaluated by human experts and LLM judges.
- Published 6 first-author papers at top-tier conferences (KDD, AMIA, AAIC, IEEE BIBM) and in health-informatics journals, with collaborative work at NeurIPS.
Research Assistant
Political Science Joint Project · UPenn × Columbia × UC Berkeley
- Engineered a robust ML pipeline on Google Cloud for multi-source Venezuelan political data (web-scraped articles, television broadcasts, audio), cutting data preparation from 4 weeks to 1.
- Fine-tuned OpenAI Whisper and GCP Speech-to-Text on Spanish political discourse, optimizing for domain terminology and varied broadcast audio quality.
- Applied transformer-based NLP to 100k+ Venezuelan news articles (2006–2009), quantifying political sentiment shifts across media sources during the Chávez era.
Data Science Intern
KPMG
- Streamlined 4 Python data pipelines for audit analysis, cutting errors by 30% and saving 16 hours per week.
- Built automated dashboards (SQL Server, Python, Power BI) tracking 20+ KPIs with one-click updates and real-time visibility.
Skills
AI / Machine Learning
PyTorch · TensorFlow · Computer Vision · Medical Imaging · Model Optimization · MLOps
NLP & LLMs
Fine-tuning (LoRA/QLoRA) · RAG · Prompt Engineering · Hugging Face · LangChain
Programming & Data
Python · SQL · Git · Linux · Docker · AWS · GCP · Apache Spark · ETL
Visualization & Analytics
ArcGIS · Tableau · Power BI · Plotly · R · MATLAB