Write and review prompts that test the line between safe and unsafe requests on energetic materials. Suits Master's-level chemical or mechanical engineers with explosives expertise who hold Five Eyes citizenship.
عن الوظيفة
<p>AfterQuery is looking for explosives and energetic materials experts to help make AI models safer in their domain. You'll author and review evaluation tasks that test whether a model can tell a safe request from an unsafe one, and write the expert analysis behind each call: what makes a prompt acceptable, where it crosses a line, and why.</p>
<p><strong>Requirements</strong></p>
<ul>
<li>Master's degree or higher in chemical engineering, chemistry, mechanical engineering, or a related discipline, with expertise in explosives or energetic materials</li>
<li>Citizenship of a Five Eyes country (United States, United Kingdom, Canada, Australia, or New Zealand)</li>
<li>Physically located in one of those countries while doing the work</li>
<li>Able to explain the technical reasoning behind a safety judgment clearly and precisely</li>
</ul>
<p><strong>Pay:</strong> $150/hr equivalent, paid at $85 per approved task. Remote, flexible, task-based.</p>
Responsibilities:
- Author prompts and scenarios that probe the boundary between safe and unsafe requests in your field
- Review and classify prompts written by other experts as safe or unsafe
- Write the domain analysis behind each judgment: why a prompt is acceptable or where it crosses a line
- Revise your work based on structured reviewer feedback
Required qualifications:
- Citizen of a Five Eyes country: United States, United Kingdom, Canada, Australia, or New Zealand
- Physically located in one of those five countries while doing the work
- Able to explain the technical reasoning behind a safety judgment clearly and precisely
- Master's degree or higher in chemical engineering, chemistry, mechanical engineering, or a related discipline, with expertise in explosives or energetic materials
المصدر الرسمي: experts.afterquery.com. قد تتغير التفاصيل؛ والكلمة الأخيرة لصفحة المنصة.هل في هذه الوظيفة خطأ؟ أخبرنا.
المزيد من وظائف الاختبار الهجومي والسلامة كل وظائف AfterQuery وظائف الفريق الأحمر والسلامة في الذكاء الاصطناعي في الولايات المتحدة وظائف في الولايات المتحدة