Adjunct Assistant Professor
Shrimai Prabhumoye is a Senior Research Scientist with the Applied Deep Learning Research group at NVIDIA and an Adjunct Faculty at Boston University. Her research is centered around building the best large language models (LLMs), and making them safe to use by reducing their toxicity and bias.
Shrimai is a lead researcher at NVIDIA working on data curation, pretraining, scaling and safe deployment of large language models. She is a core contributor in releasing Nemotron family of LLMs. The recently released Nemotron4-15B is the current state-of-the-art general purpose model in its size class on all multilingual benchmarks.
Before joining NVIDIA, she completed her PhD from Carnegie Mellon University in 2021 where she was advised by Prof. Ruslan Salakhutdinov and Prof. Alan W Black. Her thesis focused on controlling style, content and structure in text generation. She also co-designed the Computational Ethics for NLP course offered for the first time at CMU in 2019.
Check out Shrimai Prabhumoye’s personal page.