Stephen Roller


I am a member of the Technical Staff at Character.AI. My research interests include scaling large language models, and dialogue.

Previously, I worked as a Research Engineer at Meta's Fundamental AI Research (FAIR), where I was a leading member of the Large Language Model team and the dialogue team. Much of my work from that time is open source. Before FAIR, I completed my PhD in Computer Science at the University of Texas at Austin under the supervision of Katrin Erk.


I'm most easily reached via my personal email,


My scholarly publications appear below in reverse chronological order. Stars by names indicate joint first authorship.

FAIR (2017 — 2023)

PhD (2010 — 2017)

Undergrad (2010)