In machining of hard materials, surface integrity is one of the major customer requirements which comprise the study of the changes induced to the workpiece. Surface roughness and residual stress are often considered as the most significant indications of surface integrity. Inducing tensile residual stress during the machining processes is a critical problem which should be avoided or minimized to obtain better service quality and component life. This problem becomes more evident in the presence of rough machined surface because fatigue life of manufactured components might be decreased significantly. Inconel 718 superalloy is one of the hard materials used extensively in the aerospace industries. It is prone to tensile residual stress in machined surface. Thus, controlling and optimizing residual stress and surface roughness in machining of Inconel 718 are so needed. Intelligent techniques based on the predictive and optimization models can be used efficiently for this purpose. In this study, the optimal machining parameters including cutting speed, depth of cut, and feed rate were accessed by intelligent systems to evaluate the state of residual stress and surface roughness in finish turning of Inconel 718. The results of experiments and analyses indicated that implemented techniques in this work provided a robust framework for improving surface integrity in machining of Inconel 718 alloy. It was shown that cutting speed has more effect on surface integrity than other investigated parameters. Also, depth of cut and feed rate were found in the moderate range to obtain satisfactory state of tensile residual stress and surface roughness.