Adversarial Prompt Expert
Adversarial Prompt Expert is an open role at Handshake AI, with pay listed as Up to $65/hr.
About this role
As an Adversarial Prompt expert, you'll be able to participate 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 test model guardrails, exploring creative ways to bypass restrictions, and systematically documenting outcomes. You’ll think like an adversary to uncover weaknesses, while collaborating with engineers and safety researchers to share findings and improve system defenses.
Pay
Up to $65/hr
About Handshake AI
Handshake AI's connection to Handshake: Handshake AI fellowship / opportunity network. Generalist and specialist AI evaluation and training projects
Ownership confidence: Confirmed. See the full network profile →
Frequently asked questions
How do I apply for the Adversarial Prompt Expert role at Handshake AI?
Apply directly through Handshake AI's own application process — HumanSourcer links out to the listing and doesn't handle applications or hiring directly.
Is the Adversarial Prompt Expert role at Handshake AI remote?
This role is listed for: null.
What does the Adversarial Prompt Expert role at Handshake AI pay?
Handshake AI lists this role's pay as Up to $65/hr.
What kind of work is Adversarial Prompt Expert?
Other. Generalist and specialist AI evaluation and training projects
Is Handshake AI a legitimate AI-training platform?
Handshake AI's connection to Handshake: Handshake AI fellowship / opportunity network. Ownership confidence: Confirmed — verified via joinhandshake.com.