Adversarial Prompt Expert

Looking for Adversarial Prompt specialists to shape how AI handles adversarial prompt questions and reasoning.

As an Adversarial Prompt expert, you'll be able to join in in project-based opportunities focused on probing large language models for failure modes and harmful outputs. Your work will involve crafting prompts and scenarios to trial model guardrails, exploring creative ways to bypass restrictions, and systematically recording outcomes. You’ll think like an adversary to uncover weaknesses, while partnering with engineers and safety researchers to share findings and improve system defenses.

How it works

• Hourly rates start at $45 and extend up to $65 depending o