千问千问事业部-MOS 实验室-Agent Harness专家-北京/杭州/广州
社招全职2年以上技术类-开发地点:北京 | 杭州 | 广州状态:招聘
工作描述
任职要求 任职要求:我们寻找以下三类人才(具备其一即可) 类型 A:业务逻辑与提示工程专家 ● 对业务场景有极强的洞察力,善于将复杂的业务问题拆解为大模型可处理的任务逻辑。 ● 在 Prompt Engineering、上下文工程、RAG 结合方面有丰富经验,能熟练运用大模型能力解决实际痛点。 ● 具备较强的逻辑抽象能力,能设计高鲁棒性的 Agent 交互逻辑。 类型 B:系统架构与底层能力专家 ● 熟悉 Agent 框架底层机制,在虚拟化/容器化(Docker)、自动化控制(Claw / Playwright)等方向有深入实践。 ● 具备扎实的后端工程功底,能够为 Agent 提供稳定、高性能的外部工具调用环境(Tool-use Environment)。 ● 对 Agent 的安全执行沙箱、资源调度有深刻理解。 类型 C:互联…
登录查看完整工作描述
微信扫码,1秒登录
包括英文材料
大模型+
https://www.youtube.com/watch?v=xZDB1naRUlk
You will build projects with LLMs that will enable you to create dynamic interfaces, interact with vast amounts of text data, and even empower LLMs with the capability to browse the internet for research papers.
https://www.youtube.com/watch?v=zjkBMFhNj_g
Prompt+
https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/introduction-prompt-design
A prompt is a natural language request submitted to a language model to receive a response back.
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering
These techniques aren't recommended for reasoning models like gpt-5 and o-series models.
https://www.youtube.com/watch?v=LWiMwhDZ9as
Learn and master the fundamentals of Prompt Engineering and LLMs with this 5-HOUR Prompt Engineering Crash Course!
RAG+
https://www.youtube.com/watch?v=sVcwVQRHIc8
Learn how to implement RAG (Retrieval Augmented Generation) from scratch, straight from a LangChain software engineer.
AI agent+
https://www.ibm.com/think/ai-agents
Your one-stop resource for gaining in-depth knowledge and hands-on applications of AI agents.
Docker+
https://www.youtube.com/watch?v=GFgJkfScVNU
Master Docker in one course; learn about images and containers on Docker Hub, running multiple containers with Docker Compose, automating workflows with Docker Compose Watch, and much more. 🐳
https://www.youtube.com/watch?v=kTp5xUtcalw
Learn how to use Docker and Kubernetes in this complete hand-on course for beginners.
Playwright+
https://learn.microsoft.com/en-us/training/modules/build-with-playwright/
In this module, you'll learn how to use Playwright to test a sample web application.
https://playwright.dev/docs/intro
Playwright Test is an end-to-end test framework for modern web apps.
https://www.youtube.com/watch?v=hN1Zn6kLntk
还有更多 •••
相关职位
社招2年以上技术类-算法
任职要求:深耕底层原理,具备实战视野 我们寻找在 Agent 领域有深度思考的算法专家,你只需要具备以下部分经验即可: 1. 架构与原理深厚: 深刻理解 Agent 的底层逻辑(规划、记忆、工具调用)
更新于 2026-08-18北京|杭州|广州
社招1年以上技术类-算法
1. 具备丰富的搜索系统研发经验, 熟悉搜索基础算法与工程技术,对搜索业务有深刻理解。 2. 希望将深厚的搜索积淀与大模型技术结合,实现技术的代际跨越,为取得突破性的业务收益、解决真实的业务问题而兴奋
更新于 2026-09-02北京|杭州