Accurate modelling of chemical and physical interactions is crucial for obtaining thermodynamic and dynamical properties of any chemical system, enabling a myriad of possible applications. Many of these applications are computationally prohibitive when using advanced Computational Chemistry (CompChem) methods even on modern supercomputers. Because of this, machine learning (ML) force fields (FFs), combining the accuracy of state-of-the-art ab initio methods and the efficiency of classical FFs, are being increasingly used to reconstruct potential-energy surfaces (PESs) of molecules and solids. It is precisely the synergy of ML and CompChem that has revolutionized the field in the last decade, rising the applications to a qualitatively new level. Despite this great success, there are still many unsolved challenges. In this context, my research work has been focused on assessing the current limitations of MLFFs and proposing solutions to build simultaneously accurate and efficient ML models for reconstructing the complex PESs of realistic molecular systems.