Remote AI Safety Specialist — Eng & Malay Adversarial Testing

Mercor; San Francisco (CA); Híbrido; GBP 18 000 - 26 000; Tempo integral

Resumo da oferta

Mercor is seeking AI Safety Experts to probe English and Malay language models from a remote location. You will red team conversational AI, identify jailbreaks and misuse cases, and generate high-quality data to inform fixes and improvements.

You should have strong English and Malay fluency, experience in AI adversarial work, and the ability to explain risks clearly to both technical and non-technical stakeholders. This contract role offers flexible hours and remote work.

Qualificações

• Fluent in English and Malay.
• Experience in AI adversarial work (red teaming).
• Ability to explain risks to tech and non-technical stakeholders.

Responsabilidades

• Red team conversational AI models and agents to identify jailbreaks and misuse cases.
• Annotate failures, classify vulnerabilities, and flag systemic risks with high-quality data.
• Apply taxonomy-driven testing and document reproducible reports, datasets, and attack cases.

Conhecimentos

English & Malay fluency

AI adversarial red teaming

Risk communication

Descrição da oferta de emprego

Mercor is seeking AI Safety Experts to probe English and Malay language models from a remote location. You will red team conversational AI, identify jailbreaks and misuse cases, and generate high-quality data to inform fixes and improvements.

You should have strong English and Malay fluency, experience in AI adversarial work, and the ability to explain risks clearly to both technical and non-technical stakeholders. This contract role offers flexible hours and remote work.