A complete application in a minute
Tailored resume and cover letter, ready to send.
Vettedlance is seeking specialists to probe AI models for dangerous capabilities and unsafe behavior, and to write the test cases and rubrics used in safety evaluations.
You will design adversarial prompts across CBRN, cyber threat intel, OSINT, and child safety, run jailbreak tests, and grade model outputs against safety rubrics. This remote, hourly contract is part-time (10-40 hrs/week) with pay between $60 and $90 per hour, USD.
Specialists probe AI models for dangerous capabilities and unsafe behavior, and write the test cases and rubrics used in safety evaluations.
Pay: $60 - $90 / hour (USD). Paid in USD, weekly. Rate set after a short paid assessment.