Remote Adversarial AI Safety Specialist

Mercor; San Francisco (CA); Hybride; GBP 21 000 - 23 000; Plein temps

Résumé du poste

Mercor is seeking AI Safety Experts to work remotely on a contract basis. The role focuses on red-teaming conversational AI models, generating high-quality human data, and documenting findings to help clients strengthen AI systems.

English and Urdu fluency are required, with prior adversarial AI or cybersecurity experience preferred. The position offers flexible, asynchronous work and requires strong communication to explain risks to both technical and non-technical stakeholders.

Qualifications

• Native fluency in English and Urdu.
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Strong communication skills to explain risks to technical and non-technical stakeholders.

Responsabilités

• Red team conversational AI models and agents, including jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data, annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure using taxonomies, benchmarks, and playbooks to maintain testing consistency.
• Document reproducibly by producing reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Connaissances

English

Urdu

Description du poste

Mercor is seeking AI Safety Experts to work remotely on a contract basis. The role focuses on red-teaming conversational AI models, generating high-quality human data, and documenting findings to help clients strengthen AI systems.

English and Urdu fluency are required, with prior adversarial AI or cybersecurity experience preferred. The position offers flexible, asynchronous work and requires strong communication to explain risks to both technical and non-technical stakeholders.