Remote AI Safety Red Team Specialist

Obsidian; New York (NY); On-site; USD 140,000 - 210,000; Full time

Job summary

Mercor is assembling a remote red team tasked with probing AI models for vulnerabilities, bias and safety issues. You will generate high-quality data, annotate failures, and document actionable attack cases for customers. The role requires English and Vietnamese fluency, curiosity, and an adversarial mindset.

The project emphasizes safe, guided engagement with sensitive topics, with well-defined guidelines and wellness resources. Remote work is supported across the US.

Qualifications

• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Curious and adversarial mindset to push systems to breaking points.
• Structured approach using frameworks or benchmarks.
• Clear communicator to explain risks to technical and non-technical stakeholders.
• Adaptive to move 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, 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

AI adversarial work

Cybersecurity

Socio-technical probing

Structured frameworks

Clear communication

Adaptability

Job description

Mercor is assembling a remote red team tasked with probing AI models for vulnerabilities, bias and safety issues. You will generate high-quality data, annotate failures, and document actionable attack cases for customers. The role requires English and Vietnamese fluency, curiosity, and an adversarial mindset.

The project emphasizes safe, guided engagement with sensitive topics, with well-defined guidelines and wellness resources. Remote work is supported across the US.