Remote AI Safety Red Team Expert

Mercor; New York (NY); On-site; USD 120,000 - 180,000; Full time

Job summary

Mercor is building a remote red team to probe AI models with adversarial inputs. We focus on testing for jailbreaks, bias and safety vulnerabilities in conversational systems. You will generate actionable data and reports to help customers harden their AI.

Ideal candidates have AI red teaming or cybersecurity experience, love rigorous testing, and can communicate risks clearly to both technical and non-technical stakeholders. Remote collaboration across projects and clients is common.

Qualifications

• You bring prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing).
• You’re curious and adversarial: you instinctively push systems to breaking points.
• You’re structured: you use frameworks or benchmarks, not just random hacks.
• You’re communicative: you explain risks clearly to technical and non-technical stakeholders.
• You’re 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 teaming

Adversarial mindset

Structured approach

Communication skills

Adaptable

Job description

Mercor is building a remote red team to probe AI models with adversarial inputs. We focus on testing for jailbreaks, bias and safety vulnerabilities in conversational systems. You will generate actionable data and reports to help customers harden their AI.

Ideal candidates have AI red teaming or cybersecurity experience, love rigorous testing, and can communicate risks clearly to both technical and non-technical stakeholders. Remote collaboration across projects and clients is common.