Some more about me (҂◡_◡) ᕤ

I’m Rayane Boucheraine, also known as R4Y4N3, an Offensive AI Security Researcher and Red Teamer based in Algeria.

My work focuses on identifying vulnerabilities and improving the security of AI models, LLM-powered applications, and autonomous agents, particularly as these systems gain access to tools, data, and external services.

My interests span frontier model security, agentic AI security, and AI safety, with a focus on adversarial evaluations, prompt injection, MCP and agent skills security, RAG security, multi-agent systems, and authorization boundaries.

I conduct independent security research and participate in AI-focused bug bounty and red-teaming activities. My approach combines threat modeling, vulnerability analysis, adversarial testing, and reproducible proof-of-concept development to investigate security failures and understand their real-world impact.

I primarily work with Python, Rust, Go, C, and JavaScript on Linux.

I’m interested in advancing the security and safety of AI systems through practical vulnerability research, rigorous evaluations, and technical collaboration.

For AI security research, bug bounty hunting, red teaming, or technical collaborations, feel free to reach out.

Email me · Download CV · Read the blog

Contact

• GitHub: github.com/R4Y4N3
• X: @R4Y4N3___
• LinkedIn: rayane-boucheraine
• Email: r_boucheraine@estin.dz