Cybersecurity Labeling Expert

About the role

We are seeking a Cybersecurity Labeling Expert to evaluate AI‑generated conversations for potential security threats. You will work remotely, applying your offensive security expertise to determine whether flagged content crosses the line into malicious intent.

Key responsibilities

• Analyze flagged AI conversations ranging from plain text to code‑heavy exchanges.
• Assess intent and potential harm across four domains: scaled data exfiltration, ransomware, worms/self‑replicating code, and local & remote exploits.
• Identify conversations that involve proof‑of‑concept exploit development and make labeling decisions.
• Provide nuanced judgments on whether content represents legitimate security research or genuine attack intent.

Required profile

• Hands‑on offensive security background (red team, malware analysis, penetration testing, or exploit research).
• Ability to read between the lines and distinguish legitimate security work from malicious intent.
• Comfort interpreting code‑heavy discussions and handling personally identifiable information securely.
• Tier 2‑3 experience ranging from early‑career (Masters level) to senior/principal roles.
• Experience in red‑team consulting, threat‑intelligence analysis, vulnerability research, or AI‑safety labeling.

Required skills

• Red teaming
• Malware analysis
• Penetration testing
• Exploit development
• Threat‑intelligence analysis
• Vulnerability research
• Code review
• AI safety labeling
• Handling of PII

What we offer

• Hourly rate of $100‑$150
• Fully remote, flexible schedule
• Opportunity to contribute to AI safety and cybersecurity research