Remote AI Red Team Specialist Adversarial Testing & Safety

Mercor; Jakarta Pusat; Remote; IDR 1,605,709,000 - 2,140,946,000; Full time

Job summary

Mercor is seeking a remote AI red team specialist to probe conversational models for jailbreaks, prompt injections, bias, and misuse cases. You will generate high-quality data and reports to help customers strengthen AI safety.

Fluency in English and Indonesian is required, with prior red‑teaming experience and a structured approach to testing. Join a team that values rigorous methodologies and clear risk communication across projects.

Qualifications

• Prior red teaming experience in AI adversarial work.
• Curious and adversarial; push systems to breaking points.
• Structured; uses frameworks or benchmarks, not random hacks.
• Communicative; explain risks clearly to technical and non-technical stakeholders.
• Adaptable; thrive on moving 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

Red team

AI adversarial testing

Documentation

Communication

Frameworks

Job description

Mercor is seeking a remote AI red team specialist to probe conversational models for jailbreaks, prompt injections, bias, and misuse cases. You will generate high-quality data and reports to help customers strengthen AI safety.

Fluency in English and Indonesian is required, with prior red‑teaming experience and a structured approach to testing. Join a team that values rigorous methodologies and clear risk communication across projects.