Cutting temperature, machining parameters, workpiece material, and cutting tool geometry have a significant influence on the achievement of the desired quality of product at a satisfactory cost. The aim of the present study was to develop an empirical model for predicting temperature rise (Tr) and surface roughness (Ra) in terms of spindle speed (N), feed rate (F), axial depth of cut (D a), radial depth of cut (D r), and radial rake angle (γ). The experiment was conducted on Al 6061-T6 by using a high-speed steel (HSS) end cutter based on the central composite design of response surface methodology (RSM). A second order mathematical model in terms of machining parameters was developed. The Analysis of Variance (ANOVA) was used to study the performance characteristics in the machining process. The values of Prob>F less than 0.05 indicate that the model terms are significant. The experimental results indicate that the formation of surface defect in the end milling of Al 6061-T6 results from the re-deposited tool material, plucking, feed marks, micro-pits, and chip layer formation. The high quality of the surface texture is obtained in the combined conditions of high spindle speed, optimal feed rate, lower axial and radial depths of cut, and radial rake angle. Multi objective genetic algorithm (MOGA) has been applied to optimize the machining parameters that simultaneously minimize temperature rise and surface roughness. A set of Pareto-optimal solutions provides flexibility to the manufacturer and the process engineer to select the best setting based on the quality requirements and applications. A verification and validation process shows that the predicted values were found to be in good agreement with the observed values.