Remote AI Safety Red Team Expert (Adversarial ML)

Mercor; New York (NY); Remote; USD 110,000 - 170,000; Full time

Job summary

Mercor is building a red team for AI safety. This role involves testing conversational AI models with jailbreaks, prompt injections, and bias exploration. Work is remote and text-only, with clear guidelines and wellness support.

You will annotate failures, classify vulnerabilities, and document reproducible attack cases and reports to help customers strengthen their systems. Excellent language judgment and structured, guideline-driven work are essential.

Qualifications

• Native fluency in English and Marathi required.
• Experience in red team or adversarial testing is desirable.
• Ability to document reproducible test artifacts and reports.

Responsibilities

• Red team conversational AI models and jailbreaks, prompt injections, misuse cases, bias exploration.
• Annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks for consistent testing.
• Document reproducibly: produce reports, datasets, and attack cases for customers.

Skills

English fluency

Marathi fluency

Job description

Mercor is building a red team for AI safety. This role involves testing conversational AI models with jailbreaks, prompt injections, and bias exploration. Work is remote and text-only, with clear guidelines and wellness support.

You will annotate failures, classify vulnerabilities, and document reproducible attack cases and reports to help customers strengthen their systems. Excellent language judgment and structured, guideline-driven work are essential.