AI Adversarial Specialist — English and Punjabi

Job overview

The AI Adversarial Specialist role is fully remote. Compensation is $20–$22 per hour. Mercor connects creative and technical talent with leading AI research labs. The specialist red-teams conversational AI models and agents, identifies vulnerabilities and misuse risks, and produces reproducible findings. This work helps research-lab customers understand and address model failures and systemic risks.

What you'll do

• Red-team conversational AI models and agents for jailbreaks, prompt injections, misuse cases, and bias exploitation
• generate and annotate human data
• classify vulnerabilities and flag systemic risks
• apply taxonomies, benchmarks, and playbooks consistently
• document findings in reports, datasets, and attack cases for customer action.

What we're looking for

Skills & competencies

ai adversarial specialist

remote

english

punjabi

ai safety

red teaming

prompt injection

jailbreak testing

cybersecurity

vulnerability analysis

model risk

$20–$22/hr

Work arrangement

• Weekend coverage required

Why this role

Native fluency in English and Punjabi is required; prior AI adversarial, cybersecurity, or socio-technical probing experience is required.

About the employer

Mercor is hiring for this role. Industry: Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology). Sector: 54.