Jonathan is a research manager at the ML Alignment & Theory Scholars (MATS) program, where he supports fellows in producing high-quality AI Safety research. He has supported 15 fellows across 13 research projects, resulting in 3 Anthropic publications, 1 LessWrong post, 2 papers under review, and 7 ongoing projects. Previously, he earned his PhD in mathematics from the University of Southern California where he completed his thesis on embedding problems in symplectic geometry.
University of Southern California, Ph.D. Mathematics, Provost Fellow (May 2025)
Advisor: Kyler Siegel
Duke University, B.S. Mathematics, Magna Cum Laude (May 2020), Minor in Computer Science
U.S. Presidential Scholar
* denotes equal contribution