AI Adversarial Safety Specialist — Remote (English & Thai)

Mercor; Sydney; Remote; AUD 48,000 - 70,000; Full time

Job summary

Mercor is seeking AI safety experts to red-team conversational AI models and agents in a remote capacity. The role focuses on jailbreaks, prompt injections, misuse cases and bias exploitation, with responsibilities to generate data, annotate failures, and flag systemic risks.

Applicants should have experience in AI adversarial work, cybersecurity, or socio-technical risk, with strong communication skills to explain risks to diverse stakeholders and the ability to work independently across

Qualifications

• Fluent English and Thai language required.
• Prior red-teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Strong communication skills to explain risks to both technical and non-technical stakeholders.
• Adaptability to move across projects and customers.

Responsibilities

• Red team conversational AI models and agents focusing on jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data; annotate failures and flag vulnerabilities and systemic risks.
• Apply structure using taxonomies, benchmarks, and playbooks for consistent testing.
• Document reproducibly: produce reports, datasets, and attack cases for customers.
• Work independently and asynchronously; participate in high-sensitivity projects with clear guidelines and wellness resources.

Job description

Mercor is seeking AI safety experts to red-team conversational AI models and agents in a remote capacity. The role focuses on jailbreaks, prompt injections, misuse cases and bias exploitation, with responsibilities to generate data, annotate failures, and flag systemic risks.

Applicants should have experience in AI adversarial work, cybersecurity, or socio-technical risk, with strong communication skills to explain risks to diverse stakeholders and the ability to work independently across