In the field of femtosecond laser machining, it is essential to select the appropriate process parameters to obtain near thermal damage-free and high efficient machining of SiC wafer. In this work, a method of process parameter optimization for femtosecond laser machining of 4H–SiC was proposed by using the predictive ability of the Artificial Neural Network (ANN) and the optimization algorithm of the non-dominated sorting genetic algorithm (NSGA-II). Firstly, the femtosecond laser was used to fabricate microgrooves on SiC wafers, and the effects of process parameters (laser average power, scanning speed and repetition rate) on groove depth, width, heat affected zone and material removal rate were investigated. Secondly, the ANN model is established based on experimental data. Other experiments verify the accuracy of the model, and the average error in the model’s predictions is around 5%. Thirdly, Pareto optimal solutions are obtained by global optimization of the ANN model using the NSGA-II. The experimental results show that the Pareto optimal solutions are effective and reliable. This proposed method offers dependable guidance for the selecting and optimizing process parameters of high hardness and brittle materials in the field of femtosecond laser processing, and reduces the cost of selecting the appropriate processing parameters in the production process. The method can also be extended to other machining means, such as turning and milling.