JD数据
{
"schema_version": "via_ai_product_manager_jobs_v1",
"data_type": "ai_product_manager_jobs",
"job": {
"job_title": "应用人工智能工程师（企业人工智能应用）",
"job_level": "高级",AI生成
"work_category": "全职",AI生成
"department": "",
"location": "香港",
"work_mode": "现场办公",AI生成
"job_category": "AI应用软件工程师"AI生成
},
"company": {
"company_name": "凯达环球",
"company_industry": "建筑设计",
"company_size": "100-499人",
"company_website": "",
"company_description": ""
},
"compensation": {
"salary_range": {
"min": 22000,
"max": 30000,
"currency": "CNY",
"cycle": "month"
},
"benefits": ""
},
"requirements": {
"working_years": 0,
"degree": "硕士",
"language": "中英双语",AI生成
"visa_support": "",
"responsibilities": "",
"requirements_text": "Title: Applied AI Engineer (Enterprise AI Applications)\nLocation: Hong Kong (Onsite)\nRole Summary\nWe are hiring an Applied AI Engineer to build production-grade AI-enabled applications for internal users. The focus is on enterprise document intelligence and knowledge search, with strong emphasis on governance, traceability, and reliability.\nWhat You’ll Do\n•\tBuild and ship AI-enabled applications end-to-end (prototype → production)\n•\tDesign and implement retrieval-based AI workflows (semantic search / RAG / assistants)\n•\tImplement governance controls (access control, data expiry, auditability, citation/traceability)\n•\tDefine and run evaluation (offline test sets, quality metrics, failure analysis)\n•\tCollaborate with stakeholders to clarify requirements and iterate toward usable outcomes\n•\tOwn reliability basics (logging, monitoring, incident-friendly design, documentation)\nCore Requirements\n•\tStrong software engineering skills (Python preferred) with experience shipping production systems\n•\tHands-on experience with retrieval-based systems (RAG / vector search / hybrid search / reranking) or similar\n•\tSolid system design thinking: data modeling, API design, failure modes, evaluation mindset\n•\tComfortable working with ambiguous requirements and taking ownership\n•\tFluent communication in English + Chinese\nNice-to-Haves\n•\tExperience with vector databases or search engines (any of Milvus/Qdrant/pgvector/Elastic etc.)\n•\tMLOps/DevOps basics (Docker, CI/CD; Kubernetes is a plus, not a must)\n•\tFrontend experience (React or similar)\n•\tExperience with AI-assisted coding tools (e.g., Copilot/Cursor/Claude Code)\n*****************\n职位：应用人工智能工程师（企业⼈⼯智能应⽤）\n地点：香港（现场）\n角色概述\n我们正在招聘⼀名应用人工智能工程师，为内部用户构建生产级人工智能应用程序。重点是企业文档智能和知识搜索，重点是治理、可追溯性和可靠性。\n你要做什么\n•端到端构建和发布支持ai的应用程序（原型→生产）\n•设计和实现基于检索的AI工作流（语义搜索/ RAG /助手）\n•实施治理控制（访问控制、数据过期、可审核性、引用/可追溯性）\n定义并运行评估（离线测试集，质量指标，故障分析）\n•与利益相关者合作，明确需求并迭代实现可用的结果\n•自己的可靠性基础（日志，监控，事件友好型设计，文档）\n核心需求\n具备较强的软件工程技能（Python优先），有生产系统运输经验\n•具有基于检索的系统（RAG /矢量搜索/混合搜索/重新排序）或类似系统的实践经验\n•扎实的系统设计思维：数据建模，API设计，故障模式，评估思维\n•能够适应模棱两可的需求并承担责任\n•流利的中英文沟通能力\n值得拥有的\n具有矢量数据库或搜索引擎（Milvus/Qdrant/pgvector/Elastic等）的使用经验\n•mlops /DevOps基础（Docker, CI/CD； Kubernetes优先，不是必须）\n•前端经验（React或类似）\n熟练使用人工智能辅助编码工具（如Copilot/Cursor/Claude Code）\n＊＊＊＊＊＊＊＊＊＊＊＊＊＊＊＊＊",
"skills": [AI生成
"RAG与检索增强",
"编程与代码实现",
"数据库/缓存/向量库",
"部署上线与环境配置",
"AI数据安全与合规治理"
],
"preferred_qualifications": "",
"job_highlights": ""
},
"contact": {
"recruiter_name": "",
"contact_methods": [
{
"type": "apply_link",
"value": "https://www.zhipin.com/job_detail/a9cd31277a91ead20nd52t68GFdW.html"
}
]
},
"posting": {
"posting_id": "a9cd31277a91ead20nd52t68GFdW",
"post_date": "",
"hire_time": "",
"update_date": "",
"job_url": "https://www.zhipin.com/job_detail/a9cd31277a91ead20nd52t68GFdW.html"
},
"fulltext": "Title: Applied AI Engineer (Enterprise AI Applications)\nLocation: Hong Kong (Onsite)\nRole Summary\nWe are hiring an Applied AI Engineer to build production-grade AI-enabled applications for internal users. The focus is on enterprise document intelligence and knowledge search, with strong emphasis on governance, traceability, and reliability.\nWhat You’ll Do\n•\tBuild and ship AI-enabled applications end-to-end (prototype → production)\n•\tDesign and implement retrieval-based AI workflows (semantic search / RAG / assistants)\n•\tImplement governance controls (access control, data expiry, auditability, citation/traceability)\n•\tDefine and run evaluation (offline test sets, quality metrics, failure analysis)\n•\tCollaborate with stakeholders to clarify requirements and iterate toward usable outcomes\n•\tOwn reliability basics (logging, monitoring, incident-friendly design, documentation)\nCore Requirements\n•\tStrong software engineering skills (Python preferred) with experience shipping production systems\n•\tHands-on experience with retrieval-based systems (RAG / vector search / hybrid search / reranking) or similar\n•\tSolid system design thinking: data modeling, API design, failure modes, evaluation mindset\n•\tComfortable working with ambiguous requirements and taking ownership\n•\tFluent communication in English + Chinese\nNice-to-Haves\n•\tExperience with vector databases or search engines (any of Milvus/Qdrant/pgvector/Elastic etc.)\n•\tMLOps/DevOps basics (Docker, CI/CD; Kubernetes is a plus, not a must)\n•\tFrontend experience (React or similar)\n•\tExperience with AI-assisted coding tools (e.g., Copilot/Cursor/Claude Code)\n*****************\n职位：应用人工智能工程师（企业⼈⼯智能应⽤）\n地点：香港（现场）\n角色概述\n我们正在招聘⼀名应用人工智能工程师，为内部用户构建生产级人工智能应用程序。重点是企业文档智能和知识搜索，重点是治理、可追溯性和可靠性。\n你要做什么\n•端到端构建和发布支持ai的应用程序（原型→生产）\n•设计和实现基于检索的AI工作流（语义搜索/ RAG /助手）\n•实施治理控制（访问控制、数据过期、可审核性、引用/可追溯性）\n定义并运行评估（离线测试集，质量指标，故障分析）\n•与利益相关者合作，明确需求并迭代实现可用的结果\n•自己的可靠性基础（日志，监控，事件友好型设计，文档）\n核心需求\n具备较强的软件工程技能（Python优先），有生产系统运输经验\n•具有基于检索的系统（RAG /矢量搜索/混合搜索/重新排序）或类似系统的实践经验\n•扎实的系统设计思维：数据建模，API设计，故障模式，评估思维\n•能够适应模棱两可的需求并承担责任\n•流利的中英文沟通能力\n值得拥有的\n具有矢量数据库或搜索引擎（Milvus/Qdrant/pgvector/Elastic等）的使用经验\n•mlops /DevOps基础（Docker, CI/CD； Kubernetes优先，不是必须）\n•前端经验（React或类似）\n熟练使用人工智能辅助编码工具（如Copilot/Cursor/Claude Code）\n＊＊＊＊＊＊＊＊＊＊＊＊＊＊＊＊＊"
}