Bilingual AI Safety & Adversarial ML Specialist (Remote)

Mercor; Dubai; Remote; AED 81,000 - 111,000; Part time

Job summary

Mercor is seeking AI Safety Experts to perform red team testing on AI models and agents from a remote location. The role focuses on identifying jailbreaks, prompt injections, and misuse cases while generating high-quality data to inform improvements.

The ideal candidate has fluent English and Malayalam, with strong judgment on language and content accuracy, and the ability to communicate clearly to both technical and non-technical audiences. This is a contract position with global reach.

Qualifications

• Fluent language skills are required in English and Malayalam.
• Native fluency in English and Malayalam is required.
• Clear communication for technical and non-technical audiences.

Responsibilities

• 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 ensure consistent testing.
• Document reproducibly by producing reports, datasets, and attack cases for customers to act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Skills

English & Malayalam fluency

Job description

Mercor is seeking AI Safety Experts to perform red team testing on AI models and agents from a remote location. The role focuses on identifying jailbreaks, prompt injections, and misuse cases while generating high-quality data to inform improvements.

The ideal candidate has fluent English and Malayalam, with strong judgment on language and content accuracy, and the ability to communicate clearly to both technical and non-technical audiences. This is a contract position with global reach.