CFA Candidate · MSDS Student @ NYU
Data Science · Machine Learning

I’m a Master’s student in Data Science at New York University, and I serve as a section leader for the undergraduate Causal Inference course. My work bridges machine learning and data-centric systems—from interpretable vision and protein modeling to neural decoding and fairness auditing—and I care about clarity, reproducibility, and human-centered impact.
I earned my B.A. in Data Science and Computer Science, with a minor in Business Studies, at NYU. During my undergraduate years, I had the privilege of working with Daniel Berenberg in Kyunghyun Cho’s group on protein representation learning and comprehensive benchmarking for remote homology, and at NYU Langone’s CN³ Lab on neural decoding using large neural datasets. I’m currently seeking Summer 2026 Data Science / Machine Learning internships.

Data-efficient vision: compact CNN trained on only 100 images with condensation + augmentation; 98% MNIST with explainability.

Bias audit on a 120+-feature loan model; found 20pp accuracy gap; pipeline improved AUC-ROC 0.68 → 0.90 while mitigating bias.

Mobile-optimized detector with strong cross-dataset robustness; 94% test accuracy on 140K-image GAN dataset; ELA + augmentation + Grad-CAM.

NLP on 10k+ AI-related headlines; team placed 3rd among 100+ teams in a national competition.