Adversarial AI Safety Engineer (Remote)

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

Job summary

Mercor is building a remote AI red team to stress test conversational models and surface actionable vulnerabilities. The role emphasizes human data generation, structured evaluation, and clear reporting of risk.

You will work across projects with clear guidelines and wellness resources in a safety-focused environment. You will review outputs on sensitive topics and contribute reproducible artifacts to improve safety across customer deployments.

Qualifications

• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to push systems to breaking points with measurable findings.
• Ability to apply formal frameworks or benchmarks to testing.

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

Adversarial ML

Cybersecurity

Socio-technical risk

Structured testing

Job description

Mercor is building a remote AI red team to stress test conversational models and surface actionable vulnerabilities. The role emphasizes human data generation, structured evaluation, and clear reporting of risk.

You will work across projects with clear guidelines and wellness resources in a safety-focused environment. You will review outputs on sensitive topics and contribute reproducible artifacts to improve safety across customer deployments.