Job description
Alignerr • Remote
Remote, Global
$40 - $60 per hour
-
In this role, you'll probe frontier AI models to identify vulnerabilities and test how they respond to adversarial threats.
-
Analyze AI and LLM behavior under attack scenarios to understand exploitation risks and model weaknesses.
-
Investigate prompt injection, data leakage, model abuse, and system misuse to classify vulnerabilities and recommend mitigations.
-
Evaluate systems against security best practices and identify defensive gaps.
-
Work independently on task-based assessments and document your findings with clear reasoning.
Alignerr is a platform that for people to create data for frontier AI labs.