Remote AI Safety Red Team Specialist

Mercor; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Mercor is building a fully remote red team to probe AI models for safety, resilience, and ethical considerations. You will work on adversarial inputs, jailbreaks, and vulnerability discovery while producing actionable data and reproducible reports for customers.

This role involves reviewing outputs touching on bias, misinformation, or harmful behavior within a controlled, well-guided environment with topics clearly communicated before exposure.

Qualifications

• Experience in AI adversarial work or cybersecurity is a plus.
• Ability to follow taxonomies, benchmarks, and playbooks to keep testing consistent.
• Fluent in English; Danish language skills are a plus.

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

AI red teaming

Adversarial thinking

Structured testing

Clear communication

Adaptable

Job description

Mercor is building a fully remote red team to probe AI models for safety, resilience, and ethical considerations. You will work on adversarial inputs, jailbreaks, and vulnerability discovery while producing actionable data and reproducible reports for customers.

This role involves reviewing outputs touching on bias, misinformation, or harmful behavior within a controlled, well-guided environment with topics clearly communicated before exposure.