Remote AI Safety Red Team Specialist

Mercor; Lisboa; Remote; EUR 70,000 - 90,000; Full time

Job summary

Mercor is seeking a passionate AI red team specialist to stress-test conversational agents. You will simulate jailbreaks, prompt injections, and bias exploitation to surface vulnerabilities and improve safety across integrations.

You will produce reproducible artifacts, annotate failures, and follow taxonomies and playbooks to keep testing consistent. Remote across markets, you’ll collaborate with diverse teams and customers to strengthen AI systems.

Qualifications

• Red teaming experience in AI adversarial work or cybersecurity
• Curious and adversarial mindset that pushes systems to breaking points
• Structured approach using frameworks or benchmarks
• Strong communication to explain risks to diverse stakeholders
• Adaptable to moving across projects and customers

Responsibilities

• Red team conversational AI models: jailbreaks, prompt injections, misuse cases, bias exploitation
• Generate high-quality human data: annotate failures, classify vulnerabilities, flag risks
• Apply structure: follow taxonomies, benchmarks, playbooks for consistent testing
• Document reproducibly: produce reports, datasets, attack cases for customers

Skills

Red team experience

Adversarial thinking

Structured approach

Communication skills

Adaptability

Curiosity

Job description

Mercor is seeking a passionate AI red team specialist to stress-test conversational agents. You will simulate jailbreaks, prompt injections, and bias exploitation to surface vulnerabilities and improve safety across integrations.

You will produce reproducible artifacts, annotate failures, and follow taxonomies and playbooks to keep testing consistent. Remote across markets, you’ll collaborate with diverse teams and customers to strengthen AI systems.