AI Safety Red Team Specialist - Remote

Mercor; Kuala Lumpur; Remote; MYR 327,000 - 491,000; Full time

Job summary

Mercor is building a red team for a project where human data experts probe AI models with adversarial inputs to surface vulnerabilities and generate red team data that improve safety for customers.

The role involves reviewing AI outputs touching on bias, misinformation, or harmful behaviors. Work is text-based; participation in higher-sensitivity projects is optional with clear guidelines and wellness resources. Remote position with flexible collaboration across teams.

Qualifications

• Proven experience in AI adversarial testing, red teaming or cybersecurity.
• Ability to structure and document findings using frameworks or benchmarks.

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 fluency

Indonesian fluency

Red team experience

AI adversarial testing

Job description

Mercor is building a red team for a project where human data experts probe AI models with adversarial inputs to surface vulnerabilities and generate red team data that improve safety for customers.

The role involves reviewing AI outputs touching on bias, misinformation, or harmful behaviors. Work is text-based; participation in higher-sensitivity projects is optional with clear guidelines and wellness resources. Remote position with flexible collaboration across teams.