In this training session, steps to generate on-the-fly machine learning forcefield (MLFF) for NiSi-Si system will be demonstrated. NiSi-Si interface is a technologically relevant material system for complimentary metal oxide semiconductor (CMOS) device applications for its tunable Schottky barrier height at the interface. 'Two MLFFs will be trained: one focused on the known bulk phases of Ni-Si (Ni3Si, Ni2Si, NiSi, NiSi2) and the second on the fully relaxed and strained structures of the NiSi phase. The first MLFF will be used to study diffusion across a large (~500 atoms) NiSi/Si interface system by running MD simulations of 200 ps or more at different temperatures. The second MLFF will be used to calculate thermal expansion of NiSi.