Remote AI Safety Red Team Specialist

aitrainer; United States; Remote; USD 90,000 - 150,000; Full time

Job summary

Mercor is seeking a remote, security-minded contributor to join its red team for AI safety testing. You will probe conversational AI models, generate high-quality human data, and document actionable vulnerabilities.

Strong judgement of language and content is essential, with a focus on fairness, bias, and safety across multi-turn interactions. Fluent in English and Malayalam, you will adapt to diverse projects and produce reproducible reports that help customers strengthen their AI systems.

Qualifications

• Strong judgment about language and content; ability to assess AI responses for accuracy and safety.

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

Adversarial ML

Red team testing

Prompt injection

Data annotation

Technical reporting

English fluency

Malayalam fluency

Job description

Mercor is seeking a remote, security-minded contributor to join its red team for AI safety testing. You will probe conversational AI models, generate high-quality human data, and document actionable vulnerabilities.

Strong judgement of language and content is essential, with a focus on fairness, bias, and safety across multi-turn interactions. Fluent in English and Malayalam, you will adapt to diverse projects and produce reproducible reports that help customers strengthen their AI systems.