The development of data-driven turbulence models for Reynolds Averaged Navier-Stokes simulations represents a major step forward in external aerodynamics. Reynolds Averaged Navier-Stokes remains the most widely used approach in industry due to its computational efficiency, but its limitations in predicting complex flow phenomena, such as separation, shock–boundary layer interaction, and vortex dynamics, are well known. This research introduces a data-driven enhancement to traditional one-equation turbulence models, leveraging both numerical and experimental high-fidelity datasets to improve accuracy without sacrificing efficiency. The proposed approach combines the robustness of Reynolds Averaged Navier-Stokes with the adaptability of modern data-driven techniques, offering a practical industry-ready solution for aerodynamic design challenges.