I want to develop computational and human-centric approaches that advance algorithmic fairness in machine learning systems, guided by policy and regulatory considerations.

I am currently a graduate student and research assistant at Cornell Tech, where I focused on machine learning and methods for causal inference. My recent work includes building a Python package that implements performant matrix completion using novel nearest-neighbor estimators that adapt to noise and bias across settings. It’s been tested on standard benchmarks and, after having been presented at CODEML@ICML 2025, has been released for use by researchers and industry practitioners.

From 2022 to 2024, I worked as a quantitative software developer at Goldman Sachs, on the Fundamental Equities Strategies team within Goldman Sachs Asset Management (GSAM). I built financial tools and engineered data pipelines to drive investment decisions and risk management.

From 2018 to 2022, I studied Physics and Computer Science at New York University, where my research involved contemporary problems at the intersection of digital epidemiology and machine learning. I also served as a course assistant and department-appointed tutor in both the Physics and Computer Science departments.

I’m proficient in Python, Java, and C, and I adapt quickly to new tools and frameworks. Outside of work and school, I enjoy hiking and roller skating.

More about me:

• LinkedIn
• GitHub
• Google Scholar
• My Résumé
• You can reach me via email at hello [ at ] aashish [ dot ] tech

Projects and Links:

• N²: A Unified Python Package and Test Bench for Nearest Neighbor-Based Matrix Completion.
  • Package (PyPI: nsquared)
  • Paper arXiv:2506.04166.
  • Repository (GitHub)
  • Poster (Presented at CODEML@ICML 2025)
• My Fall 2021 Computer Graphics Portfolio