Hannah Arjonillo
I am currently a Physics PhD Student into modeling complex social phenomena: specifically voting patterns as of now, but generally interested in the messy intersection of human behavior & culture, technology, information, and health.
I also have six years of applied research and ML experience in biosignals, behavioral health language, EMRs.
I am actively exploring AI safety independently, with specific interests in human agency, shared reality, and everything else downstream.
Outside of work, I love watching movies, painting, and learning piano études!
Open to roles
Between roles right now — looking for my next full-time position.
Physics PhD
Hyperspectral unmixing methodologies applied to Philippine senatorial voting patterns
- Qualifying examsAUG 2026
- Candidacy exam—
- Dissertation defense—
AI safety
Focused on my SPAR project and building my AI safety literacy.
- BlueDot Technical AI SafetyOCT 2026
- SPAR — Loss of Human Agency ABMongoing
- BlueDot Biosecurityongoing