提示工程师（LLM系统、评估与安全）
Prompt Engineer (LLM Systems, Evals & Safety)
你是否希望热爱自己的工作？是否希望有所作为，产生影响，改变人们的生活？是否希望与一个相信颠覆常规、枯燥和普通的团队一起工作？
如果是这样，那么这就是你正在寻找的工作。webook.com 是沙特阿拉伯在技术、功能、敏捷性和收入方面排名第一的活动票务和体验预订平台，服务着王国最大的大型活动，销售额超过 20 亿。
职位概述
设计高质量的提示、系统指令和工具，使我们的 LLM 功能准确、安全且成本可控。你将负责评估、提示版本管理和持续改进。
主要职责：
- 编写、重构和组合提示（系统/工具/策略）以完成各种任务。
- 创建离线/在线评估框架（评分标准、黄金数据集、指标）。
- 构建带有版本控制、A/B 测试和遥测功能的提示库。
- 通过验证、约束解码和工具使用来减少幻觉。
- 实现安全性：破解/提示注入测试、内容策略检查、个人身份信息处理。
- 与工程师合作，将提示集成到生产功能中。
要求：
- 在多种任务类型和模型上展示过提示设计能力。
- 有构建评估数据集和自动化评分的经验（例如准确性、忠实性、实用性、成本/延迟）。
- 熟悉检索增强生成概念和工具/函数调用。
- 强大的脚本编写能力（Python/TypeScript），用于数据准备、评估和分析。
- 清晰的写作能力；能够将业务目标转化为可衡量的提示规范。
加分项：
- 有 LangChain/LLM 协调、向量存储和重排序器的经验。
- 了解安全工具和红队技术。
- 实验平台（功能标志、A/B 测试）、分析工具。
查看英文原文
Do you want to love what you do at work? Do you want to make a difference, an impact, and transform peoples lives? Do you want to work with a team that believes in disrupting the normal, boring, and average?
If yes, then this is the job you are looking for , webook.com is Saudi’s #1 event ticketing and experience booking platform in terms of technology, features, agility, revenue serving some of the largest mega events in the Kingdom surpassing over 2 billion in sales.
Role Overview
Design high-quality prompts, system instructions, and tooling that make our LLM features accurate, safe, and cost-effective. You’ll own evaluation, prompt versioning, and continuous improvement.
Key Responsibilities:
- Author, refactor, and chain prompts (system/tool/policy) for varied tasks.
- Create offline/online evaluation harnesses (rubrics, golden sets, metrics).
- Build prompt libraries with versioning, A/B testing, and telemetry.
- Reduce hallucinations via verification, constrained decoding, and tool use.
- Implement safety: jailbreak/prompt-injection tests, content policy checks, PII handling.
- Partner with engineers to integrate prompts into production features.
Requirements
- Demonstrated prompt design across multiple task types and models.
- Experience building eval datasets and automated scoring (e.g., accuracy, faithfulness, utility, cost/latency).
- Familiarity with retrieval-augmented generation concepts and tool/function calling.
- Strong scripting (Python/TypeScript) for data prep, evals, and analysis.
- Clear writing; ability to translate business goals into measurable prompt specs.
Nice-to-Haves
- Experience with LangChain/LLM orchestration, vector stores, and rerankers.
- Knowledge of safety tooling and red-teaming techniques.
- Experiment platforms (feature flags, A/B tests), analytics.
Originally posted on Himalayas