Remote AI Safety Specialist — Adversarial ML & Risk Vetting

mercor; United States; A distancia; USD 22.000 - 30.000; Jornada completa

Descripción de la vacante

Mercor, a San Francisco-based AI safety firm, seeks AI Safety Experts for remote contracting work across time zones. You will test and probe conversational AI models, annotate failures, and document findings to help customers strengthen defenses against misuse.

The role emphasizes high language quality, careful error detection, and independent, asynchronous work with strict guidelines and quality standards.

Formación

• Native fluency in English and Assamese.
• Strong judgment about language and content accuracy.
• Rigorous attention to subtle errors and inconsistencies.
• Ability to work to guidelines and quality standards.
• Clear communication with technical and non-technical audiences.
• Adaptability across projects and task types.

Responsabilidades

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly to produce reports, datasets, and attack cases for customer action.
• Work independently and asynchronously to enhance AI model performance and ensure flexible hours.

Conocimientos

Native fluency in English

Native fluency in Assamese

Judgment about language accuracy

Attention to subtle errors

Adherence to guidelines

Clear communication

Adaptability across projects

Descripción del empleo

Mercor, a San Francisco-based AI safety firm, seeks AI Safety Experts for remote contracting work across time zones. You will test and probe conversational AI models, annotate failures, and document findings to help customers strengthen defenses against misuse.

The role emphasizes high language quality, careful error detection, and independent, asynchronous work with strict guidelines and quality standards.