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 enterprise red teaming and

adversary emulation

● Deep knowledge of Active Directory attack paths, Kerberos abuse, credential access,

lateral movement, and privilege escalation

● Experience operating C2 frameworks (Cobalt Strike, Sliver, Mythic, Havoc) and building

payloads and loaders that evade EDR/AV

● Practical phishing and social engineering tradecraft, initial access techniques, and

operational security (OPSEC)

● Fluency with the MITRE ATT&CK framework and the ability to tell red team operations

from real-world intrusion activity

● 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

● OSEP, OSCP, CRTO

● 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.