AI Red Team Specialist — Adversarial Testing (Remote)

Mercor; San Francisco (CA); Remote; USD 130,000 - 170,000; Full time

Job summary

Mercor is seeking responders for a remote AI safety red team. You will challenge conversational AI models with jailbreaks, prompt injections, and bias exploitation, producing high-quality data and reproducible reports for customers.

Ideal candidates have red teaming experience in AI or cybersecurity, are curious and structured, and can communicate risks clearly to technical and non-technical stakeholders. Remote work is available for this role.

Qualifications

• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to push systems to breaking points in a controlled, ethical way.
• Use of frameworks or benchmarks to keep testing consistent.

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.
• Document reproducibly: produce reports, datasets, and attack cases customers can act on.

Skills

Red team experience

Adversarial AI testing

Frameworks/benchmarks

Structured communication

Adaptability

Job description

Mercor is seeking responders for a remote AI safety red team. You will challenge conversational AI models with jailbreaks, prompt injections, and bias exploitation, producing high-quality data and reproducible reports for customers.

Ideal candidates have red teaming experience in AI or cybersecurity, are curious and structured, and can communicate risks clearly to technical and non-technical stakeholders. Remote work is available for this role.