{"id":3105020,"url":"https://alion.io/job/xiaomi-zidonghuaceshi","title":"自动化测试","company":{"id":105,"name":"Xiaomi","domain":"mi.com","url":"https://alion.io/company/xiaomi","size_band":"5000+","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Feishu","truth_index":{"grade":"C","score":69,"open_postings":1068,"ghost_share":0.437,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":111,"computed_at":"2026-10-29T05:49:05Z"}},"role":"QA","role_family":"QA","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Beijing, China"],"countries":["CN"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":40000,"max":50000,"currency":"CNY","period":"month","gross":null,"usd_annual":90084},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Python","optional":false}],"status":"live","first_seen_at":"2026-10-21T06:40:02Z","employer_posted_date":null,"last_verified_at":"2026-10-21T06:40:02Z","board_verified":false,"closed_at":null,"days_open":7,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":7},"description":"职位描述\n\n（一）AI Agent全场景测试方案设计与落地\n\n1. 负责智能座舱车载AI Agent核心业务测试，覆盖多模态交互（语音、视觉、触控、手势）、对话理解、多轮对话、意图识别、槽位填充、场景联动、主动智能服务、车控指令执行、导航/娱乐/车生活场景AI决策等核心功能。\n\n2. 结合车载行车场景、驻车场景、多路况、多用户使用习惯，梳理AI Agent业务测试点，输出完整的测试方案、测试用例、场景库、风险点清单，覆盖功能测试、边界测试、异常场景测试、兼容性测试、安全合规测试。\n\n3. 针对AI Agent算法迭代、模型升级、版本迭代开展回归测试、对比测试、灰度测试，验证模型效果迭代优化情况，保障版本交付质量。\n\n（二）AI测试自动化与工具开发\n\n1. 负责搭建和维护智能座舱AI Agent自动化测试框架，开发自动化测试脚本，实现对话流程、指令执行、场景联动、响应结果的自动化回归，提升测试效率，支撑快速迭代。\n\n2. 开发、维护AI测试辅助工具，包括对话数据采集工具、测试用例批量生成工具、结果校验工具、日志解析分析工具，实现测试数据自动化处理、问题自动定位。\n\n（三）AI Agent评测体系搭建与质量度量\n\n1. 建立车载AI Agent专属评测指标体系，包括意图识别准确率、多轮对话连贯性、指令执行成功率、响应时延、误唤醒率、拒识率、场景适配率、容错性、用户体验评分等核心指标。\n\n2. 负责批量评测数据集的构建、清洗、迭代，基于真实车载场景构建差异化测试数据集，支撑模型效果量化评估。\n\n3. 定期输出AI Agent质量评测报告、版本质量报告、指标趋势分析报告，定位模型短板、业务逻辑缺陷、场景适配问题，驱动算法、产品、开发持续优化。\n\n（四）问题跟进与质量闭环管控\n\n1. 负责测试过程中缺陷的发现、定位、复现、归因，区分算法问题、前端交互问题、后台服务问题、座舱系统适配问题、链路通信问题，推动问题高效修复闭环。\n\n2. 跟进线上用户反馈、售后问题、舆情问题，复现线上AI Agent异常问题，输出问题分析结论，推动版本优化和风险规避。\n\n（五）跨团队协同与版本交付保障\n\n1. 对接AI算法团队、座舱产品团队、前后端开发团队、车载系统团队、测试团队，参与需求评审、技术方案评审、迭代复盘。\n\n2. 把控迭代版本测试准入、准出标准，评估版本质量风险，输出Release测试报告，保障座舱AI Agent功能稳定交付上车。\n\n职位要求\n\n（一）学历与专业背景\n\n1. 本科及以上学历，计算机、软件工程、人工智能、电子信息、自动化等相关专业。\n\n（二）专业能力要求\n\n1. 业务认知能力\n\n熟悉智能座舱核心业务，了解车载AI Agent工作逻辑，熟悉大模型对话、意图识别、多轮对话管理、场景智能触发、车控联动等AI业务流程；熟悉车载端、云端、服务端全链路架构，了解车载系统基础原理。\n\n2. 测试开发技术能力\n\n熟练掌握 Python 编程语言，熟悉常用自动化测试框架，能够独立开发自动化测试脚本和测试工具；熟悉接口测试、链路测试、端到端测试，掌握HTTP、MQTT等常用协议.\n\n3. AI测试专业能力\n\n熟悉NLP基础常识、大模型基础特性，了解AI模型评测基本方法；掌握AI准确率、召回率、时延、稳定性等量化评测方式，能够独立搭建AI评测体系和测试数据集；具备AI问题归因能力，可精准区分算法、工程、场景适配类问题。\n\n4. 工具与数据能力\n\n熟悉日志分析、数据清洗、批量数据处理方法；了解Git、CI/CD流程，能够适配迭代自动化测试流程；有车载测试平台、AI评测平台搭建或使用经验者优先。\n\n（三）综合素质要求\n\n1. 具备较强的需求理解能力、场景拆解能力、风险识别能力，能够快速适配AI产品快速迭代节奏。\n\n2. 逻辑清晰，善于问题复盘和经验沉淀，具备良好的文档撰写能力和汇报能力。\n\n（四）优先加分项\n\n1. 有智能座舱车载大模型、AI主动服务、多模态交互项目测试开发经验。\n\n2. 熟悉LangChain、Prompt工程、Agent智能编排、工具调用（Function Call）相关技术，了解AI Agent架构。\n\n3. 有数据集构建、模型微调评测、AI自动化评测平台搭建经验。\n\n4. 熟悉车载Android、QNX、Linux系统，有车载自动化测试、实车测试经验。","description_format":"text","description_chars":1806,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Smart Home Devices","Automotive Manufacturing","Smartphones","Televisions"],"lifecycle":[{"event":"open","at":"2026-10-22T18:37:00Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":7,"expected_fill_days":111,"reasons":["seen:7","velocity","win:early","comp:brand"],"computed_at":"2026-10-29T05:49:05Z"},"pay":{"stated_usd_annual":90084,"is_top_pay":false},"html_url":"https://alion.io/job/xiaomi-zidonghuaceshi","json_url":"https://alion.io/job/xiaomi-zidonghuaceshi.json","meta":{"generated_at":"2026-10-29T06:19:27Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":9600,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-30T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":105},"rest":"https://alion.io/mcp/rest/get_company?id=105"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fxiaomi-zidonghuaceshi"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fxiaomi-zidonghuaceshi"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fxiaomi-zidonghuaceshi"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/xiaomi-zidonghuaceshi\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fxiaomi-zidonghuaceshi"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3105020}},{"tool":"search_jobs","arguments":{"company":"mi.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3105020},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}