{"id":2715140,"url":"https://alion.io/job/cloud-i-nfra-huanjia","title":"Ai Infra 专家","company":{"id":59211,"name":"UCloud","domain":"ucloud.cn","url":"https://alion.io/company/ucloud","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Beisen","truth_index":{"grade":"B","score":75,"open_postings":17,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-19T05:45:15Z"}},"role":"DevOps","role_family":"DevOps","seniority":null,"employment_type":null,"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":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"CUTLASS","optional":false},{"name":"PyTorch","optional":false},{"name":"SGLang","optional":false},{"name":"Speculative Decoding","optional":false},{"name":"TensorRT","optional":false},{"name":"Triton","optional":false}],"status":"live","first_seen_at":"2026-10-16T11:33:19Z","employer_posted_date":"2026-10-16","last_verified_at":"2026-10-19T12:21:09Z","board_verified":true,"closed_at":null,"days_open":3,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":3},"description":"岗位职责 / Responsibilities\n职位描述\n负责LLM/VLM大模型的部署与推理性能优化，系统性降低硬件延迟瓶颈，保障高并发下线上服务稳定性（TTFT与TPOT满足SLA要求）。\n探索前沿推理加速技术，推动在新型GPU/NPU等硬件上的落地。\n任职要求 / Requirements\n职位要求\n1. 精通Python，熟悉C++，具备高性能代码开发与算法实现能力。\n2. 至少具备以下2个领域中的实践经验：\na. Transformers与Diffusers库，深入理解Attention变体（GQA、MLA、KDA、Sparse Attn）及其优化技术（FlashAttention、PagedAttention）; \nb. GPU编程（CUDA/cutlass/Triton/TileLang开发）且掌握性能分析工具（Nsight、PyTorch Profiler等）; \nc. 模型压缩（量化、稀疏化、知识蒸馏）; \nd. GPU集群通信架构（卡间通信NVLink/PCIe，机间通信RDMA/RoCE），理解NCCL、HCCL等通信库的工作机制; \n3. 符合以下条件者优先：\na. 有超大规模模型（1T参数以上）的分布式部署经验; \nb. 有推理系统经验，如为vLLM、SGLang、TensorRT-LLM贡献过核心PR; \nc. 有投机采样（Speculative Decoding）的落地与优化经验（如EAGLE、DFlash等）; \nd. 有相关开源项目、专利或论文发表; \ne. 有国产芯片（如昇腾、海光等）的在线服务加速经验。\n4. 良好的团队协作能力与工程落地能力，对技术有持续热情。","description_format":"text","description_chars":711,"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":["Data Centers & Colocation","Cloud Platforms (IaaS & PaaS)"],"lifecycle":[{"event":"open","at":"2026-10-16T13:47:40Z"}],"visa":[],"liveness":{"score":60,"band":"ok","label":"Likely open","p_open":1,"p_active":0.602,"p_room":1,"age_days":2,"expected_fill_days":22,"reasons":["conf:1","stale_co","win:early"],"computed_at":"2026-10-19T05:45:15Z"},"pay":null,"html_url":"https://alion.io/job/cloud-i-nfra-huanjia","json_url":"https://alion.io/job/cloud-i-nfra-huanjia.json","meta":{"generated_at":"2026-10-19T14:52:10Z","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":10954,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-20T00:00:00Z"}},"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":59211},"rest":"https://alion.io/mcp/rest/get_company?id=59211"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcloud-i-nfra-huanjia"},{"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%2Fcloud-i-nfra-huanjia"},{"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%2Fcloud-i-nfra-huanjia"},{"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/cloud-i-nfra-huanjia\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcloud-i-nfra-huanjia"}]}