Johns Hopkins University Applied Physics Laboratory
AI Assurance Research Intern
Two internships in AI assurance research, working on evaluation methodology for operational and healthcare AI systems.
Pathways Program Intern
- Developed sponsor-facing technical products and testing frameworks for AI evaluation projects.
- Implemented methodologies from emerging literature to support project work.
- Made technical presentations to senior experts in AI assurance; iterated based on their feedback.
- Further details available in resume upon request.
ASPIRE Program Intern
- Designed CLARION, a multi-agent Python and Flask system in which agents systematically compare responses to resolve ambiguity in natural language guidance.
- Built a Python tool using natural language processing and rule-based scoring to assess AI-generated medical responses across six health communication metrics, validated by comparing a retrieval-augmented model against a general one.
- Presented a poster at the APL Intelligent Systems Symposium (2025).