Remote AI Safety Red Team Specialist

Obsidian; Jakarta Pusat; Remote; IDR 2,143,240,000 - 2,857,653,000; Full time

Job summary

Mercor is seeking a bold AI red team specialist to probe conversational models with jailbreaks, prompt injections, and bias tests. This role is fully remote and focuses on generating actionable data to strengthen safety.

You will document findings, follow established taxonomies, and collaborate with clients to clarify risks. Prior red-teaming in AI, cybersecurity, or socio-technical domains is preferred.

Qualifications

• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to think adversarially and push systems to breaking points.
• Structured approach using frameworks or benchmarks, not ad-hoc hacks.
• Strong written and verbal communication to explain risks to technical and non-technical stakeholders.

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 teaming

Adversarial thinking

Structured testing

Clear communication

Adaptability

Job description

Mercor is seeking a bold AI red team specialist to probe conversational models with jailbreaks, prompt injections, and bias tests. This role is fully remote and focuses on generating actionable data to strengthen safety.

You will document findings, follow established taxonomies, and collaborate with clients to clarify risks. Prior red-teaming in AI, cybersecurity, or socio-technical domains is preferred.