Remote AI Safety Expert — Red Team, EN/Bengali (Contract)

Mercor; Greater London; Sur place; GBP 20 000 - 22 000; Plein temps

Résumé du poste

Mercor seeks AI Safety Experts for a remote contract role to test and stress AI systems. You will red team conversational models, identify jailbreaks and misuse patterns, and produce actionable data and reports for customers.

Fluency in English and Bengali is required, with prior adversarial AI or cybersecurity experience. Strong communication is essential to explain risks to diverse stakeholders and to drive safe, robust AI deployments.

Qualifications

• Fluent in English and Bengali.
• 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 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 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

Bengali

Description du poste

Mercor seeks AI Safety Experts for a remote contract role to test and stress AI systems. You will red team conversational models, identify jailbreaks and misuse patterns, and produce actionable data and reports for customers.

Fluency in English and Bengali is required, with prior adversarial AI or cybersecurity experience. Strong communication is essential to explain risks to diverse stakeholders and to drive safe, robust AI deployments.