Afnán Alabdulwahab
I studied Electrical and Computer Engineering as an undergraduate, and later completed a Master’s in Data Science from the University of Virginia in May 2025. Before grad school, I spent five years as a software engineer in industrial automation at GE and Emerson. I am now looking for a research role in AI safety and have been working toward that transition full-time.I’m currently exploring interpretability evaluation and improving the scientific rigor of how we measure and validate AI reasoning. I am drawn to work that brings causal inference and rigorous experimental design into interpretability research, subjecting existing tools and methods to the same level of scientific scrutiny we would expect in fields like epidemiology or clinical research. I am currently exploring this through the PRISM fellowship and am open to structured research programs, and collaborations that build both technical skills and research taste in this space.
This is where I showcase my projects and share thoughts on topics I’m exploring.