Remote AI Safety Red Team Engineer

Mercor; Singapore; Remote; SGD 90,000 - 130,000; Full time

Job summary

Mercor is building a remote red team for AI safety, focusing on adversarial testing of conversational models. This text-based work explores sensitive topics under clear guidelines, with participation optional and wellbeing resources provided.

You’ll annotate vulnerabilities, generate high-quality data, and document reproducibly to help customers harden their AI systems. Strong judgment on language and content is essential, with rigorous attention to detail and adherence to playbooks.

Qualifications

• Native fluency in English and Malayalam required.
• Strong judgment about language and content and ability to explain reasoning.
• Structured and able to follow guidelines and quality standards.

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

Malayalam fluency

Job description

Mercor is building a remote red team for AI safety, focusing on adversarial testing of conversational models. This text-based work explores sensitive topics under clear guidelines, with participation optional and wellbeing resources provided.

You’ll annotate vulnerabilities, generate high-quality data, and document reproducibly to help customers harden their AI systems. Strong judgment on language and content is essential, with rigorous attention to detail and adherence to playbooks.