What you'll do

● Review cybersecurity prompts submitted to an AI system that the system could not

confidently classify as benign or malicious

● Determine the underlying intent and goal behind each prompt, and assess whether the

user is pursuing a legitimate purpose or an intent to cause harm

● Apply deep domain expertise to judge the technical context, specificity, and real-world

uplift a response would give an attacker

● Annotate each prompt with an intent label and a clear written rationale, following the

project guidelines

● Independently annotate the same prompts as a second researcher; cases where

researchers disagree are escalated to a reviewer

● Flag ambiguous cases, emerging attack techniques, and gaps in the guidelines, and

help improve them

Requirements

● Minimum of 5 years of proven, hands-on experience in vulnerability research and

reverse engineering

● Proven ability to discover vulnerabilities through fuzzing, static and dynamic analysis,

and patch diffing

● Exploit development experience, including memory corruption, heap exploitation, ROP,

and mitigation bypasses (ASLR, DEP, CFI)

● Fluent use of IDA, Ghidra, Binary Ninja, and debuggers (WinDbg, GDB, LLDB) on

x86/x64 and ARM binaries

● Understanding of the CVE lifecycle, n-day versus 0-day work, and how public PoCs are

weaponized

● Strong analytical judgment

able to infer a user's underlying goal from a short prompt

and separate defensive, educational, and research use from attack preparation

● Clear written communication in English, with the ability to document your reasoning

concisely

Nice to have

● OSED, OSEE, GIAC GXPN

● Demonstrated online achievements, write-ups, or contributions on platforms such as

HackTheBox, Pwn2Own, TryHackMe, Bug Bounty programs, or published security

research.

View the original posting and apply on Jobs Sniper.