This paper demonstrates design of a Very Low Head axial flow turbine using surrogate-based optimization. The design variables were blade angles between guide vanes and runner blades, whereas the objective function was turbine efficiency. A Latin Hypercube Sampling method was initially used to design the experiment with thirty sampling points, and a Large Eddy Simulation was modeled to analyze the flow for all sampling points. A correlation between design variables and the turbine efficiency was then evaluated using the surrogate models while the optimal design variables were identified. Also, several optimizers were used to tackle the proposed problem and their performances were investigated. The optimal design of blade angles 18 being 10 o , 20 o , 30 o , 40 o , 25 o , 45 o , 55 o and 65 o respectively, increased the turbine efficiency up to 89.87 %. The approach of using surrogate modeling was proved to be very effective and simple for optimizing a design of blade angles of stator-rotor and it can be applied for designing any other new blades.