{"code":0,"data":{"job_post_detail":{"id":"7623375038457612607","title":"Agent 全栈开发工程师","description":"1. 基于OpenClaw框架开发企业级AI Agent，实现多场景任务自动化（知识问答、审批提醒、数据查询、会议纪要等）\n2. 开发和维护MCP Server端工具链，使Agent能安全调用内部业务系统\n3. 基于LangChain/LangGraph搭建Agent Workflow，实现复杂多步推理链路与条件分支控制\n4. 参与Agent Skills模块开发，构建可复用、可编排的企业技能库\n5. 实现Agent与飞书机器人的消息通道对接，支持多轮对话、卡片交互、文件处理\n6. 参与Agent评测用例编写与回归测试，确保Agent质量可度量、可追溯","requirement":"- 本科及以上学历，3年以上后端开发/AI应用开发经验，至少1年LLM Agent相关项目经验\n- 精通Python，熟悉TypeScript/Node.js\n- 熟练使用LangChain、LangGraph，有基于Graph的Agent状态机开发经验\n- 熟悉OpenClaw/Clawdbot框架，了解Agent Loop、Gateway、Queue等核心机制\n- 有MCP协议开发经验，能独立构建MCP Server并注册工具\n- 深入理解LLM能力边界，有Prompt Engineering实战经验\n- 熟悉Docker/K8s容器化部署，有CI/CD实践经验\n- 了解Manus Agent的多步任务执行模式、Genspark的搜索Agent架构者加分\n- 有CrewAI、AutoGen、Dify等Agent平台开发经验者加分","recruit_type":{"id":"101","name":"全职","en_name":"Full-time","i18n_name":"全职","depth":2,"parent":{"id":"1","name":"社招","en_name":"Experienced","i18n_name":"社招","depth":1,"children":[],"active_status":1,"selectability":1},"children":[],"active_status":1,"selectability":1},"publish_time":1774955803538,"channel_online_status":1,"code":"A22862A","job_id":"7623375038457497919","city_list":[{"code":"CT_11","name":"北京","en_name":"Beijing","location_type":3,"i18n_name":"北京","py_name":"beijing","mdm_code":"MDCY00000001","node_status":1}],"job_post_info":{"recruitment_type":{"id":"101","name":"全职","en_name":"Full-time","i18n_name":"全职","depth":2,"parent":{"id":"1","name":"社招","en_name":"Experienced","i18n_name":"社招","depth":1,"children":[],"active_status":1,"selectability":1},"children":[],"active_status":1,"selectability":1},"HighlightList":[],"JobChannelPublishList":[],"job_post_object_value_map":{},"address_list":[],"city_list":[],"correlation_job_list":[],"tag_list":[],"storefront_list":[],"target_major_list":[],"job_post_process_time_list":[],"job_level_id_list":[]},"city_info_list_for_delivery":[{"code":"CT_11","name":"北京","en_name":"Beijing","location_type":3,"i18n_name":"北京","py_name":"beijing","mdm_code":"MDCY00000001","node_status":1}],"tag_list":[],"storefront_mode":1,"storefront_list":[],"process_type":1},"recommend_job_post_List":[]},"message":"ok","error":null}