Cybersecurity Labeling Expert

About the role

We are seeking a Cybersecurity Labeling Expert to evaluate flagged AI conversations. You will apply your offensive security expertise to determine intent and potential harm across a range of threat domains.

Key responsibilities

• Analyze AI‑generated text and code‑heavy exchanges for signs of malicious intent.
• Assess risk across four domains: scaled data exfiltration, ransomware, worms/self‑replicating code, and local & remote exploits.
• Identify when a conversation crosses into prohibited exploit development or proof‑of‑concept work.
• Provide accurate security labels for each interaction while handling any personal data securely.

Required profile

• Hands‑on offensive security background (red team, malware analysis, penetration testing, or exploit research).
• Ability to distinguish legitimate security research from genuine attack intent.
• Comfort interpreting code‑heavy dialogues and nuanced security contexts.
• 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.
• Access to a secure review interface and capability to handle PII.

Required skills

• Red teaming
• Malware analysis
• Penetration testing
• Exploit development
• Threat intelligence
• Vulnerability research
• Code analysis

What we offer

• Hourly compensation between $100‑$150.
• Fully remote, freelance engagement.
• Flexible schedule and access to secure tooling.