Remote AI Safety Red Team Analyst

Mercor; Sydney; Remote; AUD 80,000 - 110,000; Full time

Job summary

Mercor is building a remote red team for AI safety. You will test conversational AI models with jailbreaks, prompt injections, and bias exploration, generating high-quality human data to surface vulnerabilities.

You will follow structured taxonomies and playbooks, document reproducibly with reports and datasets, and communicate findings clearly to both technical and non-technical audiences. This role suits rigorous, adaptable professionals who can shift across projects and collaborate with

Qualifications

• You can assess whether AI responses are accurate, complete and appropriate.
• You notice subtle errors, inconsistencies and gaps.
• You work to guidelines and quality standards consistently.

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

Judgment on language and content

Rigorous attention to detail

Structured and guideline-driven

Clear communicator

Adaptable across projects

Job description

Mercor is building a remote red team for AI safety. You will test conversational AI models with jailbreaks, prompt injections, and bias exploration, generating high-quality human data to surface vulnerabilities.

You will follow structured taxonomies and playbooks, document reproducibly with reports and datasets, and communicate findings clearly to both technical and non-technical audiences. This role suits rigorous, adaptable professionals who can shift across projects and collaborate with