Hi! I’m Yuxu Ge, a software engineer and AI enthusiast with over a decade of experience in backend development. My journey began in traditional computer science, and I’ve since evolved into a multidisciplinary developer working at the intersection of artificial intelligence, software architecture, and system security.

I'm a deep interest in machine learning, natural language processing, and multimodal systems. I enjoy designing practical AI pipelines that integrate LLMs, RAG (retrieval-augmented generation), and agent-based systems.

Before diving into AI, I spent many years building robust backend systems using Java, Spring Boot, and MySQL. I also have hands-on experience with cloud-native architecture, distributed systems, and performance tuning. I value clean, maintainable code and love solving complex system-level problems.

Outside of development, I’m actively learning about offensive and defensive cybersecurity techniques, including penetration testing, as part of my goal to become a more well-rounded engineer.

This blog is my space to share ideas, research, side projects, and learning reflections. Topics range from AI model design, Java engineering, to security experiments and tech philosophy.

Want to collaborate or just say hi? You can find me on GitHub