Remote AI Safety Red Team Specialist (EN/ID)

Obsidian; Jakarta Pusat; On-site; IDR 1,605,709,000 - 2,676,182,000; Full time

Job summary

Mercor is seeking a focused AI red-teamer to test conversational models, identify vulnerabilities, and produce actionable attack cases. This role involves reviewing outputs touching sensitive topics and generating high-quality data for safer AI systems.

You will work with a distributed team, apply structured playbooks, and document reproducible results. Fluent English and Indonesian are required; remote work options are available across regions.

Qualifications

• Red teaming experience in AI adversarial work or cybersecurity.
• Ability to push systems to breaking points with structured approaches.
• Clear communication of risks to technical and non-technical stakeholders.
• Adaptability to work across multiple 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 teaming experience

Adversarial mindset

Structured thinking

Clear communication

Adaptability

Tools

Adversarial ML techniques

Cybersecurity concepts

Risk analysis frameworks

Job description

Mercor is seeking a focused AI red-teamer to test conversational models, identify vulnerabilities, and produce actionable attack cases. This role involves reviewing outputs touching sensitive topics and generating high-quality data for safer AI systems.

You will work with a distributed team, apply structured playbooks, and document reproducible results. Fluent English and Indonesian are required; remote work options are available across regions.