The　rapid　integration　of　smart　devices　with　cloud　services　in　the　Industrial　Internet　of　Things　(IIoT)　has　exposed　significant　vulnerabilities　in　conventional　security　protocols,　making　them　insufficient　against　sophisticated　cyber　threats.　Despite　advancements　in　intrusion　detection　systems　(IDS),　there　remains　a　critical　need　for　highly　accurate,　adaptive,　and　scalable　solutions　for　cloud-based　IIoT　environments.　Motivated　by　this　necessity,　we　propose　an　advanced　AI-powered　IDS　leveraging　Long　Short-Term　Memory　(LSTM)　and　Gated　Recurrent　Unit　(GRU)　networks.　Developed　using　Python　and　the　Kitsune　dataset,　our　IDS　demonstrates　a　remarkable　detection　accuracy　of　98.68%,　a　low　False　Negative　rate　of　0.01%,　and　an　impressive　F1　score　of　98.62%.　Comparative　analysis　with　other　deep　learning　models　validates　the　superior　performance　of　our　approach.　This　research　contributes　significantly　to　enhancing　cybersecurity　in　cloud-based　IIoT　systems,　offering　a　robust,　scalable　solution　to　mitigate　evolving　cyber　threats.