{"id":1783201,"url":"https://alion.io/job/aidu-ituirigongchengshi","title":"AI推理工程师","company":{"id":101,"name":"Baidu","domain":"baidu.com","url":"https://alion.io/company/baidu","size_band":"5000+","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Career site","truth_index":{"grade":"C","score":62,"open_postings":1365,"ghost_share":0.555,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":62,"computed_at":"2026-10-28T05:59:10Z"}},"role":"AI/ML","role_family":"AI/ML","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":["Shenzhen, 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":"C++","optional":false},{"name":"CUDA","optional":false},{"name":"cuDNN","optional":false},{"name":"JAX","optional":false},{"name":"NCCL","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"TensorFlow","optional":false},{"name":"TensorFlow C++","optional":false},{"name":"TensorRT","optional":false},{"name":"TPU","optional":false},{"name":"Triton Inference Server","optional":false},{"name":"XLA","optional":false}],"status":"live","first_seen_at":"2026-09-14T00:00:00Z","employer_posted_date":"2026-09-14","last_verified_at":"2026-10-28T06:36:00Z","board_verified":true,"closed_at":null,"days_open":44,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":44},"description":"工作职责 / Responsibilities\n-跨平台模型部署：负责深度学习模型在 GPU（NVIDIA） 及 TPU 异构硬件平台上的推理部署、性能调优与持续迭代\n-推理性能调优：深入理解 GPU（CUDA/core 架构）与 TPU（脉动阵列/MXU）的硬件特性，针对性地解决不同架构下的性能瓶颈（访存、算子效率、芯片利用率等），提升吞吐量并降低延迟\n-技术落地与对比：参与设计和实现高效的模型推理方案，包括模型格式转换、量化（INT8/FP16/BF16）、算子融合、图优化等; 能够横向对比 GPU 与 TPU 的推理性价比与适用场景\n-跨团队协作：与算法研究团队紧密合作，推动模型结构与推理性能的协同设计（Co-design），实现算法效果与跨平台推理效率的平衡\n-工具链建设：沉淀并完善 GPU/TPU 推理部署的最佳实践，探索构建统一的推理部署工具链或抽象层，降低业务侧适配成本\n职责要求 / Requirements\n-本科及以上学历，计算机、电子工程、自动化等相关专业优先，3年以上 AI 基础设施、推理引擎或高性能计算相关经验\n-硬件理解：具备 GPU 或者 TPU 的体系架构知识，熟悉 NVIDIA GPU 的 CUDA 编程模型及底层运行机制，深入理解 TPU 或其他 AI 加速器的工作原理\n-框架熟练度：精通至少一种主流深度学习框架（PyTorch、TensorFlow 或 JAX），熟悉从模型训练到推理上线的完整流程\n-编程能力：熟练使用 C++ 和 Python，具备优秀的系统编程能力和性能调优意识\n-生态工具：GPU 方向：熟悉 TensorRT、cuDNN、NCCL 或 Triton Inference Server 等推理/服务框架; TPU 方向：熟悉 XLA（Accelerated Linear Algebra）、PyTorch/XLA 或 JAX 等 TPU 编译与运行生态","description_format":"text","description_chars":815,"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":[{"language":"Chinese","level":"Advanced (C1)","optional":false}]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Advertising","Autonomous Driving","Cloud Platforms (IaaS & PaaS)","Foundation Models"],"lifecycle":[{"event":"open","at":"2026-10-03T17:16:20Z"}],"visa":[],"liveness":{"score":31,"band":"fade","label":"Fading","p_open":1,"p_active":0.522,"p_room":0.6,"age_days":44,"expected_fill_days":62,"reasons":["conf:4","stale_co","velocity","win:late","crowd:brand"],"computed_at":"2026-10-28T05:59:10Z"},"pay":null,"html_url":"https://alion.io/job/aidu-ituirigongchengshi","json_url":"https://alion.io/job/aidu-ituirigongchengshi.json","meta":{"generated_at":"2026-10-28T11:02:52Z","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":14393,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-29T00:00:00Z"}},"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":101},"rest":"https://alion.io/mcp/rest/get_company?id=101"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Faidu-ituirigongchengshi"},{"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%2Faidu-ituirigongchengshi"},{"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%2Faidu-ituirigongchengshi"},{"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/aidu-ituirigongchengshi\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Faidu-ituirigongchengshi"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":1783201}},{"tool":"search_jobs","arguments":{"company":"baidu.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":1783201},"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"}}