Abstract: Artificial neural networks and genetic algorithms are used to model and optimize a culture medium for the production of a Poly-γ-Glutamic Acid (PGA) by Bacillus licheniformis CCRC 12826. Experimental data reported in the literature was used to build neural network model. The concentrations of four medium components served as inputs to the neural network model and the amount of poly-γ-glutamic acid concentration served as a single output of model. Genetic algorithm was used to optimize the input space of the neural network model to find the optimum settings for maximum poly-γ-glutamic acid concentration. Using this procedure, artificial intelligence techniques have been effectively integrated to create a powerful tool for process modeling and optimization.