Remote AI Adversarial Red Team Specialist

Mercor; Toronto; Remote; CAD 90,000 - 130,000; Full time

Job summary

Mercor is seeking a remote AI red team specialist to probe conversational models and identify vulnerabilities. You will annotate failures, surface risks, and generate reproducible data for safety improvements.

The role emphasizes structured testing, clear communication of risks to diverse stakeholders, and the ability to adapt across multiple projects. Fluency in English is required; Swedish is a plus.

Qualifications

• Red team experience in AI adversarial work or cybersecurity.
• Curious and adversarial: push systems to breaking points.
• Structured using frameworks or benchmarks.
• Communicative: explain risks to technical and non-technical stakeholders.
• Adaptive: thrive on moving across projects and customers.

Responsibilities

• Red team conversational AI models: jailbreaks, prompt injections, misuse cases.
• Generate high-quality human data: annotate failures and flag risks.
• Document reproducibly: reports, datasets, attack cases.
• Follow taxonomies and playbooks to keep testing consistent.

Skills

Red teaming

Cybersecurity

Socio-technical probing

Structured testing

Clear communication

Job description

Mercor is seeking a remote AI red team specialist to probe conversational models and identify vulnerabilities. You will annotate failures, surface risks, and generate reproducible data for safety improvements.

The role emphasizes structured testing, clear communication of risks to diverse stakeholders, and the ability to adapt across multiple projects. Fluency in English is required; Swedish is a plus.