The problem of optimal distribution of fibres in a fibre-reinforced composites (FRC) in order to optimise a given objective function, is investigated by using a biological-based procedure known as Genetic Algorithm (GA). A homogenisation approach, developed by taking into account the fibre–matrix interaction phenomena, is developed to obtain the mechanical properties of an equivalent homogeneous and isotropic material corresponding to the macroscopic mechanical response of the composite. The problem is studied by assuming a linear elastic mechanical composite’s behaviour, nevertheless the non-linear case may be tackled with the same strategy. The optimal fibres distribution in FRC is obtained by using a Genetic Algorithm and by searching the extreme values of a given objective function: the design optimisation of the FRC fibre’s distribution considered in the present study takes into account the maximisation of some mechanical desired performance of the structure while keeping constant the total fibre’s content (optimal constrained problem). The proposed mechanical model with the optimisation algorithm is implemented in a FE code and some numerical simulations are performed in order to assess its reliability in material’s design composition with respect to some expected optimal performance.