AI 红队专员 - 远程 | 最高 22 美元/小时
AI Red Team Specialist - Remote | Upto $22/hr
Mercor 将顶尖的创意和技术人才与领先的 AI 研究实验室连接起来。公司总部位于旧金山，我们的投资方包括 Benchmark、General Catalyst、Peter Thiel、Adam D'Angelo、Larry Summers 和 Jack Dorsey。
职位：AI 安全专家 — 英语 & 马拉地语
类型：合同工
薪资：20–22 美元/小时
地点：远程
岗位职责
- 对对话式 AI 模型和代理进行红队测试，以识别越狱、提示注入、误用案例和偏见利用。
- 通过标注失败案例、分类漏洞和标记系统性风险，生成高质量的人类数据。
- 通过遵循分类法、基准测试和操作手册来建立结构，确保测试的一致性。
- 可重复记录，生成报告、数据集和攻击案例供客户行动使用。
任职要求
必备条件
- 英语和马拉地语流利。
- 有红队经验（AI 对抗工作、网络安全、社会技术探测）。
- 能够向技术人员和非技术人员清晰解释风险。
- 适应性强，能够在不同项目和客户之间高效工作。
优先考虑
- 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。
- 社会技术风险专长：骚扰/虚假信息探测、滥用分析、对话式 AI 测试。
- 创造性探测技能：心理学、表演、为非常规对抗思维写作。
申请流程（需 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内容，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，以便考虑此机会。
最初发布于 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 & Marathi
Type:Contract
Compensation:$20–$22/hour
Location:Remote
Role Responsibilities
- Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation.
- Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
- Apply structure by following taxonomies, benchmarks, and playbooks to ensure consistent testing.
- Document reproducibly by producing reports, datasets, and attack cases for customer action.
Qualifications
Must-Have
- Fluent in English and Marathi.
- Prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing).
- Ability to explain risks clearly to technical and non-technical stakeholders.
- Adaptable and able to thrive across projects and customers.
Preferred
- Experience with 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: psychology, acting, 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