Within the broad field of personalized medicine, there has been a recent surge of clinical interest in the idea of response-guided dosing. Roughly speaking, the goal is to develop dosing strategies that administer the right dose to the right patient at the right time. In this talk, we will present several deterministic and stochastic mathematical models that attempt to formalize these types of optimal dosing problems. Theoretical results about the structure of optimal dosing strategies and associated solution methods rooted in convex optimization, stochastic dynamic programming, and Bayesian statistics will be described. Computational results on case studies in cancer radiotherapy and rheumatoid arthritis will be discussed. This is joint work with current and former students who include collaborators at the University of Washington Medical Center.