I am a PhD candidate in Reinforcement Learning at RMIT University (holding Australian PR), exploring the frontier of LLMs and Agentic RL. My mission is to engineer intelligent and reliable AI systems that combine cutting-edge research with tangible engineering impact. Before transitioning to my PhD research, I honed my technical expertise as a software engineer, architecting full-stack, cloud-native, and highly scalable backend systems. This hands-on industry experience shapes my research philosophy: I strive to bridge the divide between theoretical innovation and practical execution, ensuring the algorithms I design are both state-of-the-art and ready for real-world application.…I am a PhD candidate in Reinforcement Learning at RMIT University (holding Australian PR), exploring the frontier of LLMs and Agentic RL. My mission is to engineer intelligent and reliable AI systems that combine cutting-edge research with tangible engineering impact. Before transitioning to my PhD research, I honed my technical expertise as a software engineer, architecting full-stack, cloud-native, and highly scalable backend systems. This hands-on industry experience shapes my research philosophy: I strive to bridge the divide between theoretical innovation and practical execution, ensuring the algorithms I design are both state-of-the-art and ready for real-world application.WWWW…