The internally geared screw machine is a rotary positive displacement machine with two helical rotors rotating in the same direction on offset parallel axes. Working chambers are formed by continuous contact points, with their volume varying cyclically. By controlling the timing of fluid entry and exit, the machine achieves compression. Rotor profile design is a critical phase in compressor development, as it influences working chamber volumes, contact forces, and overall performance. Various established methods, such as the rack and pin-generation methods, use precise mathematical formulations to define rotor profiles. A more advanced approach involves deep learning. Artificial intelligence (AI) is transforming many fields, including compressor design. Recent research has demonstrated its potential in generating rack profiles for conventional screw machine rotors. However, internally geared screw machines impose additional design constraints. This paper presents a preliminary study on training a Wasserstein Generative Adversarial Network (WGAN) to generate rotor profiles that ensure continuous contact. The feasibility of this approach is demonstrated through generated profiles, and future research will explore integrating efficiency-related constraints to enhance rotor design.