Asma Ghandeharioun is a Senior Research Scientist focused on aligning AI with human values by probing, controlling, and demystifying the inner workings of language models. With nine years of research experience spanning MIT Media Lab and multiple roles at Google and Google DeepMind, she combines deep academic rigor (PhD/MAS from MIT) with practical production-facing research. Her work uniquely emphasizes correcting collective misconceptions about model behavior while developing interpretable techniques for safer language AI. Based in the New York City area, she brings a rare mix of human-centered evaluation—evident from past field studies on emotionally intelligent assistants—and mechanistic understanding that helps bridge research insights to real-world governance and deployment.
9 years of coding experience
12 years of employment as a software developer
Doctor of Philosophy (Ph.D.) MAS, Doctor of Philosophy (Ph.D.) MAS at Massachusetts Institute of Technology
Bachelor's Degree Computer Software Engineering, Bachelor's Degree Computer Software Engineering at Sharif University of Technology
This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Can Be Injected in Language Models."
Contributions:18 commits, 1 push, 1 branch in 3 months
Code to support characterizing sources of uncertainty to proxy calibration and disambiguate annotator and data bias.
Contributions:114 commits, 2 pushes in 2 years 2 months
proxyannotatorcalibrationbiasuncertainty
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Asma Ghandeharioun - Senior Research Scientist at Google DeepMind