AI Safety Expert — Adversarial Machine Learning, English and Odia
Compensation
$16 – $22 /yr
Employment type
Full-time
Work setting
On-site
Location
San Francisco, CA
Schedule
Day shift
Posted
You'll be redirected to the employer's application page.
Job overview
The AI Safety Expert — Adversarial Machine Learning, English and Odia role is fully remote. Compensation is $16–$22 per hour. Mercor connects technical and creative talent with AI research labs. The expert tests conversational AI models and agents for vulnerabilities and misuse, then produces structured annotations and reproducible reports. This work helps customers identify risks and improve AI model performance.
What you'll do
- Red-team conversational AI models and agents through jailbreak, prompt-injection, misuse, and bias testing
- annotate failures, classify vulnerabilities, and flag systemic risks
- follow taxonomies, benchmarks, and playbooks
- produce reports, datasets, and attack cases
- work independently and asynchronously.
What we're looking for
- Skills & competencies
- ai safety expertadversarial machine learningenglish and odiaremote$16–$22/hourai red teamingprompt injectionjailbreak testingvulnerability analysisai model performancetechnical documentation
- Work arrangement
- Weekend coverage required
Why this role
Native fluency in English and Odia is required. The posting says prior AI experience is not required.
About the employer
Mercor is hiring for this role. Industry: All Other Professional, Scientific, and Technical Services. Sector: 54.
Additional details
- Industry sector
- 54
- Industry
- All Other Professional, Scientific, and Technical Services
- Occupation code
- 15-1299.08
You'll be redirected to the employer's application page.
Listing ID: 91b805fa-eaa9-44b1-b7ea-59bdcd84550f