In this study, statistical models were developed using the capabilities of Response Surface Methodology (RSM) to predict the surface roughness in high-speed flat end milling of Ti-6Al-4V under dry cutting conditions. Machining was performed on a five-axis NC milling machine with a high speed attachment, using spindle speed, feed rate, and depth of cut as machining variables. The adequacy of the model was tested at 95% confidence interval. Meanwhile, a time trend was observed in residual values between model predictions and experimental data, reflecting little deviations in surface roughness prediction. A very good performance of the RSM model, in terms of agreement with experimental data, was achieved. It is observed that cutting speed has the most significant influence on surface roughness followed by feed and depth of cut. The model can be used for the analysis and prediction of the complex relationship between cutting conditions and the surface roughness in flat end milling of Ti-6Al-4V materials. The developed quadratic prediction model on surface roughness was coupled with the genetic algorithm to optimize the cutting parameters for the minimum surface roughness.