Remote AI Safety Specialist — Red Team & Adversarial Testing

Mercor; Sydney; A distancia; AUD 23.000 - 34.000; A tiempo parcial

Descripción de la vacante

Mercor, a leading talent platform for AI research, is hiring AI Safety Experts — English & Indonesian for a remote contract. You will red team AI models, generate high-quality data, annotate failures, and document findings to guide safer deployments.

Required are fluency in English and Indonesian and prior red teaming or cybersecurity experience. Strong ability to explain risks to technical and non-technical stakeholders; experience in adversarial ML is a plus. This is a remote role.

Formación

• Fluent in English and Indonesian.
• Prior red teaming or cybersecurity experience.
• Ability to explain risks clearly to technical and non-technical stakeholders.

Responsabilidades

• Red team conversational AI models and agents. Focus on 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. Produce reports, datasets, and attack cases for customer action.

Conocimientos

English fluency

Indonesian fluency

Descripción del empleo

Mercor, a leading talent platform for AI research, is hiring AI Safety Experts — English & Indonesian for a remote contract. You will red team AI models, generate high-quality data, annotate failures, and document findings to guide safer deployments.

Required are fluency in English and Indonesian and prior red teaming or cybersecurity experience. Strong ability to explain risks to technical and non-technical stakeholders; experience in adversarial ML is a plus. This is a remote role.