Remote AI Safety Red Team Specialist

Mercor; New York (NY); Remote; USD 85,000 - 120,000; Full time

Job summary

Mercor is building a remote AI red team to test and strengthen safety for conversational models. This role involves evaluating AI outputs for bias, safety risks, and failure modes in a text-based setting.

You’ll jailbreak, prompt-inject, and explore adversarial scenarios, generating high-quality data and reproducible reports. Fluency in English and Kannada is required, plus strong judgment and clear communication across technical audiences.

Qualifications

• Proven ability to assess AI outputs for accuracy, completeness and safety.
• Attention to subtle errors, inconsistencies and gaps.
• Ability to follow guidelines and quality standards.

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

Red team thinking

Adversarial testing

Strong judgment

Rigorous attention

Structured communication

Adaptability

Job description

Mercor is building a remote AI red team to test and strengthen safety for conversational models. This role involves evaluating AI outputs for bias, safety risks, and failure modes in a text-based setting.

You’ll jailbreak, prompt-inject, and explore adversarial scenarios, generating high-quality data and reproducible reports. Fluency in English and Kannada is required, plus strong judgment and clear communication across technical audiences.