Job descriptionWe're looking for highly accomplished **Cybersecurity Research Experts** to help evaluate cutting-edge AI systems in advanced security reasoning, vulnerability analysis, exploit development, and secure software engineering. This project is ideal for practitioners with a strong track record in offensive security research and publicly recognised technical contributions. ### What You'll Do - Evaluate AI-generated analyses of complex cybersecurity scenarios, exploits, and vulnerability reports. - Review technical writeups for correctness, exploitability, and mitigation quality. - Validate vulnerability root-cause analysis across software, operating systems, networking, cloud, and web applications. - Provide structured feedback on security reasoning, exploit chains, and defensive recommendations. - Contribute to benchmark development for advanced AI security capabilities. ### Ideal Background We are looking for candidates with **multiple** of the following credentials: - Member of a **top-ranked Capture The Flag (CTF)** team with demonstrated competitive achievements. - Discoverer or co-author of **CVEs** affecting widely used open-source or commercial software. - Publicly recognised **bug bounty** researcher with findings accepted by major programs (e.g., Google, Microsoft, Apple, Meta, GitHub, Mozilla, Chromium, Kubernetes, Linux Foundation, etc.). - Research experience at a **well-respected security laboratory or academic research group** (e.g., KAIST Security Lab, SSLab, university security research groups, or equivalent industry research organisations). - Author of high-quality **security research publications**, conference papers, or widely cited technical writeups. - Strong understanding of exploit development, reverse engineering, binary analysis, vulnerability research, operating systems, networks, web security, or cryptography. ### Preferred Qualifications - Professional experience in offensive security, application security, vulnerability research, product security, or security engineering. - Experience with reverse engineering tools such as IDA Pro, Ghidra, Binary Ninja, or Radare2. - Familiarity with fuzzing, symbolic execution, static analysis, or dynamic analysis frameworks. - Experience with Linux internals, Windows internals, browser security, cloud security, embedded security, or mobile security. - Strong programming skills in C/C++, Rust, Python, Go, or Java. - Excellent written communication and ability to explain complex security concepts clearly. ### Nice to Have - Hall of Fame recognition from major bug bounty programs. - Black Hat, DEF CON, USENIX Security, IEEE S&P, ACM CCS, NDSS, or similar conference presentations/publications. - Maintainer or significant contributor to well-known open-source security tools. - Offensive Security certifications (OSCP, OSEP, OSCE3), GIAC certifications, or equivalent credentials. ### Why Join? - Work on frontier AI models tackling real-world cybersecurity problems. - Collaborate with leading researchers on advanced security evaluation tasks. - Help shape the next generation of AI systems for cybersecurity.