Remote AI Safety Red Team Specialist

Neon; United States; Remote; USD 90,000 - 130,000; Full time

Job summary

Mercor is assembling a remote-friendly red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data to make AI safer for customers.

This text-based project involves reviewing AI outputs on sensitive topics; participation in higher-sensitivity tasks is optional and guided by clear guidelines. You will document reproducible reports and follow established taxonomies to keep testing consistent.

Qualifications

• Native fluency in English and Malayalam is required for this position.
• 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

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

English

Malayalam

Job description

Mercor is assembling a remote-friendly red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data to make AI safer for customers.

This text-based project involves reviewing AI outputs on sensitive topics; participation in higher-sensitivity tasks is optional and guided by clear guidelines. You will document reproducible reports and follow established taxonomies to keep testing consistent.