AI Safety Expert — Adversarial Machine Learning

Job overview

The AI Safety Expert — Adversarial Machine Learning role is remote; the posting identifies the work as remote without specifying a narrower geographic scope. Pay is $16–$22 per hour. Mercor connects creative and technical talent with leading AI research labs. The expert red-teams conversational AI models and agents, identifies vulnerabilities and misuse risks, and produces structured findings that customers can act on. The work supports consistent safety testing and improvements to AI model performance.

What you'll do

• Red-team conversational AI models and agents
• identify jailbreaks, prompt injections, misuse cases, and bias exploitation
• annotate failures and classify vulnerabilities
• follow testing taxonomies, benchmarks, and playbooks
• document reproducible reports, datasets, and attack cases
• work independently and asynchronously to meet deadlines.

What we're looking for

Skills & competencies

ai safety expert

adversarial machine learning

remote

english

gujarati

red teaming

prompt injection

jailbreak testing

ai model safety

vulnerability analysis

cybersecurity

$16–$22/hr

mercor

Work arrangement

• Weekend coverage required

Why this role

Requires native fluency in English and Gujarati; preferred experience includes adversarial machine learning, cybersecurity, and conversational AI testing.

About the employer

Mercor is hiring for this role. Industry: Employment Placement Agencies. Sector: 56.