Remote AI Safety Red Team Specialist

Mercor; Toronto; On-site; CAD 154,000 - 224,000; Full time

Job summary

Mercor is seeking a remote AI safety role focused on red-teaming conversational models. You will diagnose vulnerabilities, annotate failures, and generate actionable data to strengthen AI systems. The candidate should bring AI adversarial experience, curiosity, and a structured, communicative approach across projects.

Join Mercor to help advance safer AI and collaborate with clients across various industries while working remotely.

Qualifications

• Prior red teaming experience in AI adversarial work or cybersecurity.
• You are curious and adversarial, pushing systems to breaking points.
• You use frameworks or benchmarks, not random hacks.
• You communicate risks clearly to technical and non-technical stakeholders.
• You thrive across projects and customers.

Responsibilities

• Red team conversational AI models and agents: jailbreaks, prompt injections, misuse cases, bias exploitation, multi-turn manipulation.
• Generate high-quality human data: annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure: follow taxonomies, benchmarks, and playbooks to keep testing consistent.
• Document reproducibly: produce reports, datasets, and attack cases customers can act on.

Skills

English (fluent)

Portuguese (global)

Red team experience

Adversarial AI

Cybersecurity

Structured frameworks

Communication

Adaptability

Job description

Mercor is seeking a remote AI safety role focused on red-teaming conversational models. You will diagnose vulnerabilities, annotate failures, and generate actionable data to strengthen AI systems. The candidate should bring AI adversarial experience, curiosity, and a structured, communicative approach across projects.

Join Mercor to help advance safer AI and collaborate with clients across various industries while working remotely.