AI Safety Red Team Engineer - Remote

Mercor; Johannesburg; On-site; ZAR 1,453,000 - 2,098,000; Full time

Job summary

Mercor is building a remote AI safety red team to rigorously test conversational models. You will expose vulnerabilities, annotate failures, and contribute to datasets and reports that help customers strengthen their AI systems.

The role demands prior red-teaming experience and a structured, communicative approach to documenting risks for diverse stakeholders across multiple projects.

Qualifications

• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Structured thinker who uses frameworks or benchmarks, not ad-hoc hacks.
• Clear communicator who explains risks to both technical and non-technical stakeholders.
• Adaptable and able to move across projects and customers.

Responsibilities

• Red team conversational AI models and agents: jailbreaking, 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

AI security

Cybersecurity

Adversarial thinking

Job description

Mercor is building a remote AI safety red team to rigorously test conversational models. You will expose vulnerabilities, annotate failures, and contribute to datasets and reports that help customers strengthen their AI systems.

The role demands prior red-teaming experience and a structured, communicative approach to documenting risks for diverse stakeholders across multiple projects.