Computational methods become essential in the face of complex problems where human intuition and traditional methods fail. Recent works present artificial neural networks capable of efficiently performing tasks intractable by conventional algorithms using machine learning, rendering it one of the most popular methods. Concomitantly, genetic algorithms, inspired by the biological processes of natural selection and mutation, have been used as a metaheuristic method to find solutions to optimization problems. We then raise the question of whether genetic algorithms have the potential to solve problems in the context of quantum computing, where human intuition decreases as physical systems grow. Specifically, we focus on the evolution of quantum error-correcting codes within the stabilizer code formalism. By specifying an appropriate fitness function, we show that we can evolve celebrated codes, such as the Perfect and Shor s code with respectively 5 and 9 qubits, in addition to new unanticipated examples. Additionally, we compared it with a brute force random search and verified an increasing superiority of the genetic algorithm as the total number of qubits increases. Given the results, we foresee that genetic algorithms can become valuable tools to perform complex applications in quantum systems and produce tailored circuits that satisfy restrictions imposed by hardware.