Amy works at the intersection of natural language processing and educational measurement. Her work spans a number of applications of AI in education, ranging from automated essay scoring and NLP-based writing feedback to crisis detection in student writing, as well as measurement applications such as dyslexia screening. Her research is always centered on how psychometrics and machine learning can be combined to better support learning and student well-being.

Most recently, Amy served as Lead Scientist and Manager of Applied Language Modeling & Evaluation at Cambium Assessment, and before that as Director of Research and Partnerships for the Rapid Online Assessment of Reading (ROAR) project at Stanford University. Amy holds a Ph.D. in Research and Evaluation Methodology from the University of Colorado Boulder, with additional training in Human Language Technology, and completed a postdoctoral fellowship at Stanford University School of Medicine.