{"id":1231846,"url":"https://alion.io/job/inimax-aas-iagoushi","title":"MaaS 架构师","company":{"id":110,"name":"MiniMax","domain":"minimax.io","url":"https://alion.io/company/minimax","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Feishu","truth_index":{"grade":"B","score":78,"open_postings":147,"ghost_share":0.286,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":120,"computed_at":"2026-10-24T06:02:35Z"}},"role":"Backend","role_family":"Backend","seniority":"senior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Shanghai, China"],"countries":["CN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":34000,"max_usd":89000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":21},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"C++","optional":false},{"name":"CUDA","optional":false},{"name":"Kubernetes","optional":false},{"name":"KV Cache","optional":false},{"name":"LLM","optional":false},{"name":"Mixture of Experts","optional":false},{"name":"NCCL","optional":false},{"name":"Python","optional":false},{"name":"Ray Serve","optional":false},{"name":"SGLang","optional":false},{"name":"Speculative Decoding","optional":false},{"name":"TensorRT-LLM","optional":false},{"name":"Triton","optional":false},{"name":"vLLM","optional":false},{"name":"Ray","optional":true},{"name":"TensorRT","optional":true}],"status":"live","first_seen_at":"2026-06-22T09:35:11Z","employer_posted_date":"2026-09-25","last_verified_at":"2026-10-24T06:53:39Z","board_verified":true,"closed_at":null,"days_open":123,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":123},"description":"岗位职责 / Responsibilities\n作为 MaaS 架构师，你将全面负责大模型线上服务的全链路架构设计与质量保障，构建高性能、高可用、可弹性伸缩的模型服务平台，确保模型在生产环境中的 SLA、延迟、吞吐量达到业界领先水平。工作包括不限于：\n-负责 MaaS 平台架构设计，明确模型从产出到上线的全链路环节，对模型服务的 SLA、延迟、吞吐量等核心指标负责\n-主导大模型推理网关的设计与建设，包括多模型路由、流量调度、优先级队列、多租户隔离与 Token 级计量能力\n-设计 GPU 资源弹性伸缩策略，结合模型特征与负载信号实现智能调度与资源高效利用\n-推动 KV Cache 感知调度的方案设计与落地，包括 Prefix Caching、Paged Attention 等技术在生产环境的应用，提升显存利用率与系统吞吐\n-参与单机推理框架的选型、适配与性能调优，跟进 vLLM / TensorRT-LLM / SGLang 等主流引擎的演进，推动 Continuous Batching、Speculative Decoding、量化部署等优化落地\n-构建推理负载的统一抽象与服务化封装，支持 LLM / 多模态 / Embedding 等多种负载类型的标准化部署与可观测性建设\n任职要求 / Requirements\n本科及以上学历，计算机科学或相关专业，5 年以上后端架构或 AI 基础设施相关经验\n精通 C++ / Python / Go 中至少两门语言，具备扎实的系统编程能力\n深刻理解LLM原理（Attention 机制、KV Cache、Batching 策略等）\n具备大规模 GPU 集群的架构设计与调度经验，熟悉 Kubernetes 及 GPU 相关调度机制\n熟悉至少一种主流推理框架（vLLM / TensorRT-LLM / SGLang），有源码级理解或定制开发经验\n具备良好的跨团队协作与技术方案推动能力\n加分项:\n有千卡以上规模 GPU 推理平台的建设经验\n有自研或深度定制推理引擎的经历\n在 LLM Serving 相关开源项目中有贡献（vLLM / SGLang / Ray Serve 等）\n了解 MoE 模型推理、长上下文推理（128K+）的工程优化实践\n熟悉 CUDA / NCCL / Triton 等 GPU 编程与通信框架","description_format":"text","description_chars":990,"description_truncated":false,"requirements":{"experience_years_min":5,"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":["Shared Mobility","LLM & Generative AI","Conversational AI","Generative Audio & Music"],"lifecycle":[{"event":"open","at":"2026-09-25T15:13:22Z"}],"visa":[],"liveness":{"score":35,"band":"fade","label":"Fading","p_open":1,"p_active":0.797,"p_room":0.44,"age_days":123,"expected_fill_days":120,"reasons":["conf:3","velocity","win:tail","crowd:brand"],"computed_at":"2026-10-24T06:02:35Z"},"pay":null,"html_url":"https://alion.io/job/inimax-aas-iagoushi","json_url":"https://alion.io/job/inimax-aas-iagoushi.json","meta":{"generated_at":"2026-10-24T07:53:36Z","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":11679,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-25T00:00:00Z"}},"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":110},"rest":"https://alion.io/mcp/rest/get_company?id=110"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Finimax-aas-iagoushi"},{"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%2Finimax-aas-iagoushi"},{"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%2Finimax-aas-iagoushi"},{"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/inimax-aas-iagoushi\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Finimax-aas-iagoushi"}]}