Experience
Cornell Generative AI Lab
August 2026 – PresentApplied AI Researcher
Ithaca, NY
- Researching context management systems for long horizon agents to mitigate entity binding failures & governance decay
MotherDuck
May 2026 – August 2026Software Engineering Intern
New York, NY
- Built the internal evaluation harness to benchmark AI agents across 40 MotherDuck tasks over the CLI & MCP
- Examined failed agent trajectories to write CLI guides for 3 features, taking task category accuracies from ~16% to 100%
- Reduced agent token cost on the MotherDuck CLI up to 57% through A/B testing 5 output design principles
- Designed & shipped CLI secret management commands, enabling AI agents to deploy workflows without seeing credentials
Vanasse Hangen Brustlin, Inc.
January 2026 – May 2026Software Engineering Intern
Remote/Raleigh, NC
- Designed an agentic PDF-to-form pipeline for car crash reports, cutting analyst time by 66% over 10k+ crashes annually
- Engineered an automated geocoder & RAG classification layer w/ project docs as context, achieving ~90% accuracy
Duke University
August 2024 – December 2024Research Intern
Durham, NC
- Published first-author IEEE paper on CNN ensemble for Multiple Sclerosis diagnosis; 97.5% accuracy & 97.8% AUC-ROC
- Fine-tuned VGG19/ResNet50 layers via depth-wise separable convolutions, reducing model size 14x for edge deployment
- Injected Gaussian white noise alongside rotation, shear, and zoom augmentation to improve generalization by up to 7%
NC State University
February 2024 – September 2024Research Intern
Raleigh, NC
- Implemented knowledge distillation on a skin cancer classifier via temperature-scaled KL divergence + cross-entropy loss, lifting accuracy 19% & bias 37% while compressing model size 18x & maintaining sub-10s inference on Raspberry Pi 4
- Trained a generative adversarial network to synthesize training data, improving overall performance score by 13%