We develop methods and software tools to use machine learning techniques to obtain high-quality inter-atomic potentials fit on a minimal set of data using accurate ab-initio methods. The work will be based on the Gaussian moment neural network (GM-NN) approach developed in the Kästner group. Developing machine-learned inter-atomic potentials for room-temperature ionic liquids presents a challenge due to their complicated atomic structure and thermodynamic properties. The challenge comes in their complex potential energy surface, which, due to ionic liquids typically high viscosity, takes long simulations to adequately map with ab-initio methods. Therefore, the development of these potentials requires optimization of each stage of the machine learning workflow, including data generation, selection, representation, and ML algorithm deployment and active learning approaches for model refinement. The methods developed here will subsequently support other applications in chemistry, catalysis, surface science, and beyond. Within PN6, our project is clearly application-oriented. It contributes to RQ1 of PN6 (ML4Sim) by incorporating physical constraints (invariance of the energy with respect to translation, rotation, and the exchange of like atoms) into the ML framework. Within the whole of SimTech, our project deals with FC1 (multi-X methods) via its contributions to materials science. Especially the molecular dynamics side of the project addresses FC3 (bridging data-poor and data-rich regimes) by exploiting a limited number of ab-initio training data to obtain physical properties of ionic liquids in different length and time scales. Overall, the project would fit both PN3 and PN6. Following the main interests of the doctoral researchers involved, we aim to associate Christian Holm’s part of the project with PN3 while Johannes Kästner’s part with PN6. Our developments will enter the MDSuite and MLSuite in the Holm group and the GM-NN (https://gitlab.com/zaverkin_v/gmnn) suite in the Kästner group.