Remote AI Safety Red Team Specialist

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

Job summary

Mercor is assembling a red team focused on AI safety, conducting adversarial testing on conversational AI models and agents. You will explore jailbreaks, prompt injections, misuse cases, and bias exploitation in a text-based environment.

You will generate high-quality human data, annotate failures, and flag systemic risks, using structured frameworks and playbooks to ensure repeatable results across projects. Remote-friendly role with wellness resources and global collaboration.

Qualifications

• Proven red-teaming or AI adversarial testing experience.
• Ability to push systems to failure points and identify weaknesses.

Responsibilities

• Red team conversational AI models and agents: jailbreaks, prompt injections, misuse cases, bias exploitation.
• 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 adversarial work

Cybersecurity

Structured testing

Clear communication

Adaptability

Adversarial thinking

Documentation

Tools

Penetration testing

Reverse engineering

Job description

Mercor is assembling a red team focused on AI safety, conducting adversarial testing on conversational AI models and agents. You will explore jailbreaks, prompt injections, misuse cases, and bias exploitation in a text-based environment.

You will generate high-quality human data, annotate failures, and flag systemic risks, using structured frameworks and playbooks to ensure repeatable results across projects. Remote-friendly role with wellness resources and global collaboration.