Adversarial Prompt Expert

Overview

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.

Details

• Hourly rates start at $45 and extend up to $65 depending on prior experience with adversarial testing.
• The position is remote and largely asynchronous. Work from wherever you are, and set your own schedule. There will be some synchronous meetings that are highly recommended to ensure your success on the projects.
• Flexible hours and the ability to work remotely, but ideally able to commit 10+ hours per week.
• Project work includes but is not limited to developing domain-specific prompts and evaluating LLM responses.
• Dedicate time researching topics that are interesting to you, with the assistance of AI.
• Learn new skills while contributing to the changing world of AI across various disciplines.
• Placement into a project will be dependent on project availability.

Qualifications

• Heavy LLM Usage — hands-on experience with multiple models (open- and closed-source), comfort experimenting across systems.
• Prompt Engineering & Jailbreaking — skill in crafting prompts, evasion techniques, and creative ways to bypass restrictions.
• Adversarial / Security Mindset — ability to think like an attacker, with bonus points for any red teaming or offensive security background.
• Persistence & Creativity — willingness to try many variations, think outside the box, and push edge cases.
• Clear Documentation — ability to log attempts and outcomes systematically, and communicate issues clearly.
• Ethical Awareness — understands boundaries and handles sensitive content responsibly. This program is open to U.S.-based candidates, and recent graduates with US work authorization.