Remote AI Safety Red Team Specialist

Mercor; Johannesburg; On-site; ZAR 350,000 - 520,000; Full time

Job summary

Mercor is seeking a remote AI red team data expert to probe conversational AI models, uncover vulnerabilities, and generate high-quality data for safety testing. This role focuses on annotating failures, following taxonomies, and documenting reproducible reports for customers.

You bring prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing), curiosity, and structured thinking.

Qualifications

• Experience in red teaming AI adversarial work or cybersecurity.
• Ability to annotate failures, classify vulnerabilities, and flag systemic risks.
• Strong structured thinking; use of frameworks/benchmarks for testing.

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 for customers.

Skills

English

Portuguese

Job description

Mercor is seeking a remote AI red team data expert to probe conversational AI models, uncover vulnerabilities, and generate high-quality data for safety testing. This role focuses on annotating failures, following taxonomies, and documenting reproducible reports for customers.

You bring prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing), curiosity, and structured thinking.