Remote AI Safety Red Team Specialist

Obsidian; New York (NY); Remote; USD 120,000 - 170,000; Full time

Job summary

Mercor is seeking a security-minded red team expert to probe AI systems and surface vulnerabilities before deployment. You will simulate jailbreaks, prompt injections, and misuse scenarios while producing structured, actionable data for customers.

You’ll document findings with reproducible reports, collaborate with diverse teams, and adapt across projects and clients, contributing to safer AI experiences worldwide.

Qualifications

• Experience conducting red-team or adversarial testing on AI systems.
• Ability to follow benchmarks, taxonomies, and playbooks.
• Strong writing skills for reproducible reports and datasets.
• Comfort explaining risks to technical and non-technical stakeholders.

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 team experience

Curious/adversarial mindset

Structured thinker

Clear communicator

Adaptable across projects

Tools

Adversarial ML

Cybersecurity

Socio-technical risk

Creative probing

Job description

Mercor is seeking a security-minded red team expert to probe AI systems and surface vulnerabilities before deployment. You will simulate jailbreaks, prompt injections, and misuse scenarios while producing structured, actionable data for customers.

You’ll document findings with reproducible reports, collaborate with diverse teams, and adapt across projects and clients, contributing to safer AI experiences worldwide.