For me, AI evaluation is ultimately about language, meaning, and relationship. I'm fascinated by how people and AI communicate—how understanding succeeds, where it falters, and how trust is established through language.
I work in AI evaluation, with a background in philosophy, theology, literature, writing, and education. The philosopher and ethicist in me is drawn to understanding human-AI interaction: evaluating model behavior, crafting prompts, identifying ambiguity, and translating complex ideas into language that is clear, useful, and grounded.
Over the past several months, I've had the privilege of evaluating frontier language models across multiple platforms. I've learned to apply detailed rubrics while exploring the calibration behind them and the evaluation methodologies that influence outcomes. As I investigate how prompt design shapes model behavior, I write structured rationales and draw on my background in critical thinking, logical reasoning, and careful analysis.
Before working in AI evaluation, I spent many years teaching, writing, and creating art. Those experiences continue to shape the way I approach evaluation: with curiosity, careful observation, and respect for nuance.
Resume