Adversarial Prompt Specialist for AI Model Evaluation

• Develop and implement prompts and scenarios to probe large language models.
• Identify and document failure modes and harmful outputs.
• Collaborate with engineers and safety researchers to improve model defenses.
• Explore creative methods to bypass model restrictions., Role Overview As a Legal Specialist, you will leverage your legal expertise to contribute to a transformative project aimed at enhancing AI capabilities. Your role will involve c…
• 3 days ago

• Experience with large language models and their applications.
• Strong analytical and problem-solving skills.
• Ability to think creatively and adopt an adversarial perspective.
• Excellent documentation and communication skills.

• Part-time remote position.
• Project-based engagement with flexible hours.

Compensation Up to $65/hr (depending on the project). Eligibility Open to candidates with relevant experience and skills in the field.