The goal of this talk is to present a framework for building software-defined radios that are able to self-optimize their parameters using evolutionary algorithms. As part of a student research project, such a system has been implemented on the basis of the DEAP library for Python. The talk will discuss the goal of this framework, describe the overall system architecture, and present a system prototype that has been employed to optimize radio transmission parameters in an unknown radio environment in order to maximize the achievable throughput. The current prototype targets Iris-based SDRs. However, as the entire software is Python-based and employs standard components for interfacing the SDR, it can easily be ported to GNU Radio or other SDR frameworks. We will also present some preliminary results that have been obtained through over-the-air experiments in which we optimized different power parameters (HW and SW gain stages) and modulation and coding scheme in an unknown radio environment.