AI Safety Red Team Specialist (EN/ID) – Remote

mercor; Indonesia; Remote; IDR 418,948,000 - 616,100,000; Full time

Job summary

Mercor is seeking AI Safety Experts to join our remote team on a contract basis. The role concentrates on red-teaming conversational AI, testing jailbreaks, prompt injections, misuse scenarios, and bias vulnerabilities, with English and Indonesian language requirements.

You will generate high-quality data, annotate failures, and document reproducible reports and attack cases to support responsible AI deployment.

Qualifications

• Fluent in English and Indonesian; able to explain risks to technical and non-technical stakeholders.
• Red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.

Responsibilities

• Red team conversational AI models and agents; focus on jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data; annotate failures, classify vulnerabilities, and flag systemic risks.
• Document reproducibly; produce reports, datasets, and attack cases for customer action.

Skills

Red Teaming

Cybersecurity

Bilingual English/Indonesian

Job description

Mercor is seeking AI Safety Experts to join our remote team on a contract basis. The role concentrates on red-teaming conversational AI, testing jailbreaks, prompt injections, misuse scenarios, and bias vulnerabilities, with English and Indonesian language requirements.

You will generate high-quality data, annotate failures, and document reproducible reports and attack cases to support responsible AI deployment.