Adversarial AI Test Engineer Remote

Mercor
Remote United States Full-time 🌐 English
ME
Salary: $116k - $116k/year
Experience: Entry-level
Added to JobCollate: March 21, 2026

AI Summary Powered by Gemini

This role involves evaluating AI models by probing for vulnerabilities using adversarial inputs and generating data to classify failures. Key requirements include fluency in English and Hebrew, and prior experience in AI adversarial work or cybersecurity.

Job Description

Evaluate AI models by probing with adversarial inputs to surface vulnerabilities and enhance safety. Generate human data by annotating failures and classifying vulnerabilities. Apply structured frameworks and benchmarks to maintain consistent testing.RequirementsFluent in English and Hebrew.Prior experience in AI adversarial work, cybersecurity, or socio-technical probing.Strong communication skills to explain risks to both technical and non-technical stakeholders.Originally posted on Himalayas

Full Description

Evaluate AI models by probing with adversarial inputs to surface vulnerabilities and enhance safety. Generate human data by annotating failures and classifying vulnerabilities. Apply structured frameworks and benchmarks to maintain consistent testing.RequirementsFluent in English and Hebrew.Prior experience in AI adversarial work, cybersecurity, or socio-technical probing.Strong communication skills to explain risks to both technical and non-technical stakeholders.Originally posted on Himalayas

Required Skills

Remote-Test-Automation-Engineer Remote-Software-Development-Engineer-In-Test Remote-Quality-Assurance-Engineer Remote-QA-Engineer Test-Engineer