Remote AI Safety Red Team Specialist

Mercor; Dubai; Remote; AED 150,000 - 190,000; Full time

Job summary

Mercor is building a dedicated red team to probe AI models with adversarial inputs and surface vulnerabilities. This role involves reviewing AI outputs on sensitive topics and generating red team data to strengthen safety for customers.

As a remote position, you will annotate failures, classify vulnerabilities, and document reproducible reports and attack cases, adhering to strict guidelines and quality standards.

Qualifications

• Strong judgment about language and content; ability to judge AI responses for accuracy, completeness, and safety.
• Rigorous attention to subtle errors, inconsistencies and gaps.
• Structured approach following guidelines and quality standards, not ad hoc.
• Excellent written/spoken communication to explain reasoning to technical and non-technical audiences.

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

Judgment and reasoning

Rigorous attention to detail

Structured approach

Clear communication

Adaptability

Job description

Mercor is building a dedicated red team to probe AI models with adversarial inputs and surface vulnerabilities. This role involves reviewing AI outputs on sensitive topics and generating red team data to strengthen safety for customers.

As a remote position, you will annotate failures, classify vulnerabilities, and document reproducible reports and attack cases, adhering to strict guidelines and quality standards.