Remote AI Safety Red Team Engineer

Neon; United States; Remote; USD 120,000 - 190,000; Full time

Job summary

Mercor is assembling a remote red team to test and strengthen AI systems through adversarial inputs. You will annotate failures, classify vulnerabilities, and surface systemic risks using rigorous taxonomies and playbooks.

The role rewards clear communication of risks to both technical and non-technical stakeholders. You bring prior AI adversarial red-team experience, curiosity, and a structured approach, thriving across different projects and customers while delivering high-quality data and

Qualifications

• Prior red teaming experience in AI adversarial work or cybersecurity.
• Curious and adversarial; you instinctively push systems to breaking points.
• Structured thinker; uses benchmarks or frameworks, not random hacks.
• Able to explain risks clearly to technical and non-technical stakeholders.
• Adaptable; comfortable 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

AI adversarial

Cybersecurity

Socio-technical probing

Structured thinking

Communication

Adaptability

Job description

Mercor is assembling a remote red team to test and strengthen AI systems through adversarial inputs. You will annotate failures, classify vulnerabilities, and surface systemic risks using rigorous taxonomies and playbooks.

The role rewards clear communication of risks to both technical and non-technical stakeholders. You bring prior AI adversarial red-team experience, curiosity, and a structured approach, thriving across different projects and customers while delivering high-quality data and