Security Labeling Specialist – Remote (Contract)

About the role

Mercor is seeking a Security Labeling Specialist to work remotely on a short‑term contract. You will apply your offensive security expertise to label AI‑generated content, helping improve safety classifiers for advanced language models.

Key responsibilities

• Analyze flagged AI conversations to assess intent and potential harm, covering topics such as data exfiltration, ransomware, worms, and exploits.
• Evaluate proof‑of‑concept exploit development and distinguish between legitimate security research and malicious intent.
• Provide accurate ground‑truth labels that feed into AI safety classifiers.
• Work independently and asynchronously, meeting weekly hour commitments and deadline expectations.
• Collaborate with other security experts to ensure consistent threat assessments and labeling quality.

Required profile

• Hands‑on offensive security background (red teaming, malware analysis, penetration testing, or exploit research).
• Ability to differentiate legitimate security work from genuine attack intent.
• Comfort interpreting code‑heavy conversations.
• Education ranging from a master’s degree to early‑career through senior/principal experience.

Required skills

• Red teaming
• Malware analysis
• Penetration testing
• Exploit development
• Threat assessment

What we offer

• Hourly rate of $100–$150
• Weekly payment via Stripe Connect
• Fully remote work with flexible scheduling
• Opportunity to impact AI safety at leading research labs