对抗性AI专员 - 全程远程 | 最高22美元/小时
Adversarial AI Specialist - Fully Remote | Upto $22/hr
关于职位
Mercor将顶尖的创意和技术人才与领先的AI研究实验室联系起来。公司总部位于旧金山，我们的投资者包括Benchmark、General Catalyst、Peter Thiel、Adam D'Angelo、Larry Summers和Jack Dorsey。
职位：AI安全专家 — 英语和乌尔都语
类型：合同工
薪酬：20–22美元/小时
地点：远程办公
岗位职责
- 对对话式AI模型和代理进行红队测试。执行越狱、提示注入、滥用案例和偏见利用。
- 生成高质量的人类数据。标注失败案例，分类漏洞，并标记系统性风险。
- 使用分类法、基准测试和操作手册来保持测试的一致性。
- 可重复记录。生成客户可以采取行动的报告、数据集和攻击案例。
- 独立且异步工作，以满足截止日期并提升AI模型性能。
资格要求
必须具备
- 英语和乌尔都语的母语级流利程度。
- 在AI对抗工作、网络安全或社会技术探测方面有红队经验。
- 强大的沟通能力，能够向技术和非技术利益相关者解释风险。
优先考虑
- 具有对抗性机器学习经验：越狱数据集、提示注入、RLHF/DPO攻击、模型提取。
- 网络安全背景：渗透测试、漏洞开发、逆向工程。
- 社会技术风险专业知识：骚扰/虚假信息探测、滥用分析、对话式AI测试。
- 在心理学、表演或写作方面的创造性探测技能，用于非常规的对抗性思维。
申请流程（需要20–30分钟完成）
- 上传简历
- 基于简历的AI面试
- 提交表单
资源与支持
- 有关面试流程和平台信息的详细信息，请查看：
- 如有任何帮助或支持，请联系：
备注：我们团队每天都会审核申请。请完成AI面试和申请步骤，以考虑此机会。
最初发布在Himalayas
查看英文原文
About the job
Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.
Position: AI Safety Experts — English & Urdu
Type:Contract
Compensation:$20–$22/hour
Location:Remote
Role Responsibilities
- Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.
- Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
- Apply structure using taxonomies, benchmarks, and playbooks to maintain testing consistency.
- Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.
- Work independently and asynchronously to meet deadlines while improving AI model performance.
Qualifications
Must-Have
- Native fluency in English and Urdu.
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
- Strong communication skills to explain risks to technical and non-technical stakeholders.
Preferred
- Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
- Background in Cybersecurity: penetration testing, exploit development, reverse engineering.
- Expertise in socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
- Creative probing skills in psychology, acting, or writing for unconventional adversarial thinking.
Application Process (Takes 20–30 mins to complete)
- Upload resume
- AI interview based on your resume
- Submit form
Resources & Support
- For details about the interview process and platform information, please check:
- For any help or support, reach out to:
PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.
Originally posted on Himalayas