Interested in AI Safety, Formal Verification, or discussing Alignment Faking? I am ready to collaborate with the AIM Intelligence team.
bjh3641@gmail.com
+82 10-5326-2465
Seoul, South Korea
Sogang University, Department of Mathematics
Formal Methods: Applying mathematical rigor to AI Safety guarantees.
Red Teaming: Designing evaluation pipelines for "Alignment Faking".
Engineering: Bridging abstract research with scalable, production-grade code (EntropyMath).
Building leaderboards (EntropyMath) and designing novel metrics for "Honest" reasoning in Agents.
Experience presenting at international venues (ISIS 2025) and collaborating in English.
I am eager to contribute my mathematical background and engineering skills to AIM Intelligence's mission of securing the AI ecosystem.