Remote AI Adversarial Red Team Analyst

Obsidian; Kuala Lumpur; Remote; MYR 409,000 - 654,000; Full time

Job summary

Mercor is assembling a remote red team to probe AI models for safety. You’ll jailbreak conversational agents, test prompt injections, and explore bias and misuse cases, all through text-based exercises.

You’ll annotate failures, classify vulnerabilities, and produce reproducible reports and datasets that help customers strengthen their AI systems. Clear communication to technical and non-technical stakeholders is essential.

Qualifications

• Native fluency in English and Indonesian is required.
• Experience in red teaming AI, cybersecurity, or socio-technical probing is preferred.
• Ability to use frameworks or benchmarks to test adversarial scenarios.
• Strong written and verbal communication to explain risks to diverse 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

English

Indonesian

Red team experience

Job description

Mercor is assembling a remote red team to probe AI models for safety. You’ll jailbreak conversational agents, test prompt injections, and explore bias and misuse cases, all through text-based exercises.

You’ll annotate failures, classify vulnerabilities, and produce reproducible reports and datasets that help customers strengthen their AI systems. Clear communication to technical and non-technical stakeholders is essential.