Currently, I am doing master’s in Data Science @ New York University, Center for Data Science.
I work on how to align model internals with human reasoning so AI is legible, reliable, and controllable. My work centers on AI safety (e.g., mechanistic analyses, safety interventions), and Federated Learning for privacy-preserving deployment.
Previously, I worked as a Research Intern @ Thera VR Inc., ML Intern @ Prodigy InfoTech, ML Engineer Intern at Janaki Soft.
When I’m not coding, I’m likely hiking trails - it keeps me grounded and inspired.