Up to $65/hrHandshake AIRemoteOpen to US residents
At a glance
You will probe large language models by crafting adversarial prompts and scenarios to test guardrails and bypass restrictions, documenting outcomes and sharing findings with engineers and safety researchers.
Summary written by AI from the original listing.
Posted Mar 10, 2025
About the 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.
Applicant countries
Open to US residents
This remote listing states no location restriction, so US residents can apply. Check the original listing for other requirements.
Work arrangement
Remote
Advertised job location
Not specified
Originally posted
2025-03-10
Last checked
How this pay compares
Other specialties: typical hourly pay on each platform, November 2026.
This role Up to $65/hrTypical across platforms $55/hr
micro1$55/hr112 rolesMiddle half of roles: $40–$73/hr
Mercor$51/hr80 rolesMiddle half of roles: $44–$95/hr
Turing$15/hr18 rolesMiddle half of roles: $15–$15/hr
Alignerr$80/hr81 rolesMiddle half of roles: $38–$80/hr
$0$25$50$75$100/hr
Typical (median)Middle half of roles
Based on 291 hourly-paid roles listed in November 2026. Per-task and project rates are not included. Each platform sets its own pay.