Project Lion - 提示工程师负责人 - 美国（远程，兼职）
Project Lion - Lead Prompt Engineer - United States (Remote, Part-Time)
我们正在寻找一位经验丰富的首席提示工程师，负责指导和管理团队完成整个技术迁移过程，将模板转换为LLM自动评分系统。在此职位中，您将利用先进的提示工程技巧和客户的内部工具来优化模型性能，确保AI系统的成功集成和持续改进。作为团队负责人，您将制定战略，指导初级工程师，并在塑造我们的AI驱动解决方案的未来方面发挥关键作用。
联邦法律合规
根据联邦法律，所有被聘用人员将需要：
- 验证身份及在美国工作的资格；以及
- 完成必要的就业资格验证表格。
请注意，根据联邦法律（I-9流程）要求验证工作授权，所有新员工必须在入职前三天内通过视频进行实时验证，并提供所选身份证件的照片。
了解更多详情（点击此处）
职责：
- 使用自动提示生成（APG）工具为复杂的父子模板集群创建基准提示。
- 运行并监督自动化提示优化（APO）工具，审查输出结果，并在APO出现死锁或停滞时进行标记。
- 手动撰写、测试和优化提示，以应对复杂的模板架构，克服反模式，并处理工具缺失或失效时的边缘情况。通过设计和优化手动提示解决边缘案例场景。
- 监控shadowbot运行，确保足够的分歧（人类与LLM评分之间的差异）被记录、生成和跟踪。
- 将提示版本应用于已建立的黄金数据，持续测量自动评分器质量与人类群体基准的对比，计算准确率指标如F1分数、精确率和召回率。
- 为最终版本起草技术上线准备理由（上线认证文档）。
要求：
- 语言能力：英语母语水平。
- 地点：必须位于美国。
- 教育：计算机科学、数据科学、计算语言学、人机交互（HCI）、认知科学或相关分析领域的硕士或博士学位。
- 提示工程与AI专业知识：至少7年提示工程师经验。有为严格、结构化任务调优大型语言模型（LLMs）的实操经验。
查看英文原文
We are looking for an experienced Lead Prompt Engineer to guide and manage a team through the full technical migration process, transitioning templates to LLM autoraters. In this role, you will leverage advanced prompt engineering techniques and the client’s internal tools to optimize model performance, ensuring the successful integration and ongoing enhancement of AI systems. As the team lead, you will drive the strategy, mentor junior engineers, and play a key role in shaping the future of our AI-driven solutions.
Federal Law Compliance
In compliance with federal law, all persons hired will be required to:
- Verify identity and eligibility to work in the United States; and
- Complete a required employment eligibility verification form.
Please note that in order to verify work authorization as is required by Federal law (I-9 process), all new employees must complete a live video verification with their selected IDs and provide photos of these selected IDs within their first 3 days of employment.
To know more details (Click here)
Responsibilities:
- Utilize Automatic Prompt Generation (APG) tools to create baseline prompts for complex parent-child template clusters.
- Run and supervise Automated Prompt Optimization (APO) tool, review the outputs, and flag when the APO reaches deadlocks or plateaus.
- Manually draft, test, and refine prompts to navigate complex template architectures, overcome anti-patterns, and handle edge cases where tooling is lacking or broken. Solve edge-case scenarios by designing and refining manual prompts.
- Monitor shadowbot runs to ensure sufficient disagreements (between human and LLM ratings) are registered, generated, and tracked.
- Run prompt versions against established gold data to continuously measure autorater quality against the human crowd baseline, calculating accuracy metrics such as F1 scores, precision, and recall.
- Draft technical launch readiness justifications (Launch Certification Documentation) for final.
Requirement:
- Language Skills: Native fluency in English.
- Location: Must be based in United States.
- Education: Master’s, or Doctorate degree in Computer Science, Data Science, Computational Linguistics, Human-Computer Interaction (HCI), Cognitive Science, or a related analytical field.
- Prompt Engineering & AI Expertise: At least 7 years' experience as Prompt Engineer. Proven experience tuning Large Language Models (LLMs) for strict, structured outputs, complex classification tasks, and familiarity with chain-of-thought and few-shot learning.
- Data Analysis: Strong proficiency in identifying error patterns, analyzing model performance, and using SQL or other data analytics tools.
- Technical Agility: Ability to quickly learn and master proprietary tools with minimal supervision.
- Communication: Excellent verbal and written communication skills.
Optional / Preferred Skills:
- Familiarity with enterprise-grade LLM interfaces like the Goose API.
- Experience in AI model evaluation, data science, computational linguistics, or software engineering.
- Hands-on experience with Automated Prompt Optimization (APO) systems or tuning workflows.
- Linguistic expertise, including an understanding of semantics and logic.