Remote AI Safety Red Team Analyst

Mercor; Kuala Lumpur; Remote; MYR 327,000 - 450,000; Full time

Benefits offered by this job

Adversarial ML experience preferred

Cybersecurity exposure

Job summary

Mercor is building a remote AI red team to probe conversational systems for vulnerabilities, safety gaps, and bias. You will generate high-quality human data, annotate failures, and document reproducible attack cases to help strengthen customers' AI safety.

The role emphasizes rigorous evaluation, clear reasoning, and adherence to testing playbooks across diverse projects, with a focus on responsible disclosure and wellness resources.

Qualifications

• Native fluency in English and Tamil required.
• Strong judgment about language and content.

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

Tamil

Job description

Mercor is building a remote AI red team to probe conversational systems for vulnerabilities, safety gaps, and bias. You will generate high-quality human data, annotate failures, and document reproducible attack cases to help strengthen customers' AI safety.

The role emphasizes rigorous evaluation, clear reasoning, and adherence to testing playbooks across diverse projects, with a focus on responsible disclosure and wellness resources.