Remote AI Safety Red Team Engineer

Mercor; San Francisco (CA); Remoto; USD 90.000 - 130.000; Tempo pieno

Descrizione del lavoro

Mercor is building a red team for AI safety. The role focuses on adversarial testing of conversational AI, examining jailbreaks, prompt injections, biases, and misuse cases. Work is text-based and allows remote collaboration with teams across clients.

You will generate high-quality human data, annotate failures, and document vulnerabilities using established taxonomies and playbooks to ensure reproducible, actionable findings for customers.

Competenze

• Prior red-teaming experience in AI adversarial work or cybersecurity.
• Ability to surface vulnerabilities and document them clearly.
• Familiarity with taxonomies, benchmarks and playbooks.

Mansioni

• 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

Conoscenze

Red teaming

Adversarial AI

Cybersecurity

Structured thinking

Technical communication

Descrizione del lavoro

Mercor is building a red team for AI safety. The role focuses on adversarial testing of conversational AI, examining jailbreaks, prompt injections, biases, and misuse cases. Work is text-based and allows remote collaboration with teams across clients.

You will generate high-quality human data, annotate failures, and document vulnerabilities using established taxonomies and playbooks to ensure reproducible, actionable findings for customers.