Shaz Furniturewala

I’m an MS in Data Science student at NYU’s Center for Data Science. I work on making language models fairer, more honest, and better aligned with how humans actually think and communicate. I’m particularly interested in NLP, fairness in language models, and mechanistic interpretability.

Previously, I was an AI Research Engineer at AlphaSense. Before that, I studied Computer Science at BITS Pilani, where I also TA’d Graph Mining and Neural Networks. During my undergrad I spent a year doing research at the SMOL Lab at the National University of Singapore with Prof. Kokil Jaidka, and the summer before that at Adobe’s MDSR Lab. My work has been published at EMNLP, ACL, AAAI, and ICWSM.

Outside research, I have strong opinions about sci-fi and fantasy books, and I take board games perhaps more seriously than I should.