Background & expertise
I am an ML research and measurement scientist working on AI evaluation and human-centered AI. My scientific background spans machine learning, psychometrics, applied measurement, and behavioral science.
Prior to my current role, my published research included applications of machine learning to educational measurement, as well as studies of psychological constructs, human behavior, and quantitative methodology. These disciplines share a concern with how complex phenomena can be operationalized, measured, and understood through empirical evidence.
I view measurement science as the foundation for AI evaluation and development. Many questions now central to AI evaluation and development have been studied in psychometrics and measurement science for decades, in other contexts. These methods, applied directly or adapted to questions specific to AI, can help guide the development of systems that better reflect human needs and values.
Methodological expertise
Machine learning
Predictive modeling, supervised learning, and statistical learning.
Measurement science
Psychometrics, construct operationalization, reliability, and validity.
Quantitative methodology
Statistical modeling, multivariate analysis, and empirical validation.
Behavioral science
Experimental design, psychological research, and mixed-methods research.
Research & collaboration
I welcome scientific conversations and professional inquiries.
