Remote AI Red Team Safety Specialist: Adversarial Testing

Obsidian; San Francisco (CA); Remote; USD 90,000 - 130,000; Full time

Job summary

Mercor is seeking a remote red-team data expert to probe AI models with adversarial inputs, surface vulnerabilities, and generate high-quality data for safer AI systems. English and Thai fluency are required, with topics ranging from bias to harmful content handled under clear guidelines.

You’ll document results and collaborate across projects for robust safety testing. This role focuses on reproducible artifacts, standardized taxonomies, and cross-functional communication to stakeholders,

Qualifications

• Prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing).
• Curious and adversarial: you instinctively push systems to breaking points.
• Structured: you use frameworks or benchmarks, not just random hacks.
• Communicative: you explain risks clearly to technical and non-technical stakeholders.
• Adaptable: thrive on moving across projects and customers.

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

Red team

Adversarial AI

Cybersecurity

Socio-technical risk

Structured testing

Clear communication

Adaptable

Job description

Mercor is seeking a remote red-team data expert to probe AI models with adversarial inputs, surface vulnerabilities, and generate high-quality data for safer AI systems. English and Thai fluency are required, with topics ranging from bias to harmful content handled under clear guidelines.

You’ll document results and collaborate across projects for robust safety testing. This role focuses on reproducible artifacts, standardized taxonomies, and cross-functional communication to stakeholders,