- 🌱 I'm currently learning mechanistic interpretability, GNN-based detection architectures, and multi-turn benchmark design
- 👯 I'm looking to collaborate on AI safety evaluations, benchmark design, and adversarial robustness research
- 💬 Ask me about AI safety evals, surgical AI, or how to break into AI safety research from a non-traditional background
- 📫 How to reach me: my.isabella.luong@gmail.com · LinkedIn · Portfolio
- 😄 Pronouns: she/her
- ⚡ Fun fact: I won 4 national/international competitions before pivoting into AI research — including ranking 1st twice at a McKinsey fellowship and building Vietnam's first blockchain blood donation network
- Account merged from an older school account earlier this year
