I currently work as a Research Engineer at Meta Superintelligence Labs in the Trust & Safety org. I have been working on:

  1. SFT & Online RL recipes to align voice models.
  2. Memorization evals and mitigations.

I finished my Master’s degree from Language Technologies Institute, Carnegie Mellon University. I was fortunate to be advised by Prof. Ruslan Salakhutdinov, Prof. Carolyn Rose and Dr. Denis Newman-Griffis during my time at CMU.

I’ve had the pleasure of interning at:

  • Allen Institute for AI (AllenNLP team), Summer 2022
  • Microsoft, Summer 2018, 2019

I was a community lead for the AI Safety & Alignment cohort at Cohere for AI. I am a 2018 Google Women Techmakers Scholar. I also volunteered with ACM-W for a while.