{"id":3450947,"url":"https://alion.io/job/tencent-aipingcefuzerenagentomoxingfangxiang","title":"AI评测负责人（Agent/大模型方向）","company":{"id":103,"name":"Tencent","domain":"tencent.com","url":"https://alion.io/company/tencent","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Career site","truth_index":{"grade":"B","score":76,"open_postings":62,"ghost_share":0,"stale_share":0.935,"repost_share":0.016,"time_to_fill_p50_days":47,"computed_at":"2026-11-04T06:34:25Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"junior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Shenzhen, China"],"countries":["CN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":2,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Function Calling","optional":false},{"name":"LLM","optional":false},{"name":"LoRA","optional":false},{"name":"Python","optional":false},{"name":"RLHF","optional":false},{"name":"SFT","optional":false},{"name":"Transformers","optional":false},{"name":"Windows","optional":false},{"name":"PEFT","optional":true}],"status":"live","first_seen_at":"2026-10-29T11:01:41Z","employer_posted_date":"2026-10-29","last_verified_at":"2026-11-04T18:10:57Z","board_verified":true,"closed_at":null,"days_open":6,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":6},"description":"岗位职责 / Responsibilities\n1.统筹腾讯电脑管家系列 Agent（如管家云端 Agent、磁盘清理专家等）以及自研微调模型的 AI 评测与质量保障工作，对产品和模型的效果质量负责; \n2.规划并主导 AI 评测体系建设，制定中长期路线图，覆盖模型能力评测、Agent 任务评测和端到端产品评测; 牵头制定评测标准、指标体系和评测流程，构建贴合业务的自有 Benchmark; \n3.建立评测驱动的研发机制：把评测结果接入模型迭代、Agent 发版和 CI 流程，设定安全红线和质量门禁; 为产品决策、模型选型和微调方向提供数据依据; \n4.主导评测工程平台建设，包括评测集管理、评测执行器、判分器（规则判分、状态比对、LLM-as-Judge 及人工校准）和线上采样评测; 打通“线上 trace、Bad Case 挖掘、回归评测集”的闭环; \n5.打通线上反馈闭环：从用户真实 trace、负反馈、Bad Case 中挖掘问题，持续沉淀为回归评测集。组建并带领评测团队，推动评测结论落地为实际改进; \n6.研判业界评测基准与方法的演进趋势，例如 SWE-bench Verified / Pro、Terminal-Bench、OSWorld、Windows Agent Arena、τ-bench、OS-Harm，识别公开基准的饱和与数据污染问题，结合业务做适配与创新，并对外沉淀技术影响力。\n岗位要求 / Requirements\n1.本科及以上学历，计算机科学、软件工程、人工智能或相关专业，硕士优先; \n2.5 年以上质量保障、算法评测或相关领域经验，其中有 2 年 LLM 或 Agent 评测经验更佳; 有从零搭建评测体系并推动落地的完整经历; \n3.2 年以上团队管理或技术牵头经验，能带领团队完成目标; 较好的跨团队沟通与推动能力; \n4.深入理解主流 LLM/Agent 评测基准与方法论，能清楚说明各类判分方式的取舍; 熟悉 pass@k、pass^k、LLM-as-Judge 校准、数据污染防治等关键问题; \n5.理解大语言模型的基本原理（Transformer、预训练、SFT/LoRA 微调、RLHF、推理优化），熟悉 ReAct、Function Calling、Tool Use、Planning、多 Agent 协作等 Agent 核心概念; \n6.熟练掌握 Python，具备评测平台或自动化测试框架的架构设计能力。","description_format":"text","description_chars":1036,"description_truncated":false,"requirements":{"experience_years_min":2,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[{"language":"Chinese","level":"Advanced (C1)","optional":false}]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Cloud Platforms (IaaS & PaaS)","Payment Processing & Gateways","Game Development","Esports"],"lifecycle":[{"event":"open","at":"2026-10-29T11:01:41Z"}],"visa":[],"liveness":{"score":63,"band":"ok","label":"Likely open","p_open":1,"p_active":0.632,"p_room":1,"age_days":5,"expected_fill_days":47,"reasons":["conf:2","stale_co","velocity","win:early","comp:junior,brand"],"computed_at":"2026-11-04T06:34:25Z"},"pay":null,"html_url":"https://alion.io/job/tencent-aipingcefuzerenagentomoxingfangxiang","json_url":"https://alion.io/job/tencent-aipingcefuzerenagentomoxingfangxiang.json","meta":{"generated_at":"2026-11-04T21:21:11Z","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":33054,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-05T00:00:00Z"}},"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":103},"rest":"https://alion.io/mcp/rest/get_company?id=103"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Ftencent-aipingcefuzerenagentomoxingfangxiang"},{"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%2Ftencent-aipingcefuzerenagentomoxingfangxiang"},{"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%2Ftencent-aipingcefuzerenagentomoxingfangxiang"},{"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/tencent-aipingcefuzerenagentomoxingfangxiang\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ftencent-aipingcefuzerenagentomoxingfangxiang"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3450947}},{"tool":"search_jobs","arguments":{"company":"tencent.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3450947},"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"}}