{"id":1785517,"url":"https://alion.io/job/agibot-ai-infrastructure-lead","title":"AI Infrastructure Lead","company":{"id":65142,"name":"AgiBot","domain":"agibot.com.cn","url":"https://alion.io/company/agibot-com-cn","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Feishu","truth_index":{"grade":"A","score":92,"open_postings":345,"ghost_share":0.043,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":204,"computed_at":"2026-10-22T06:10:10Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"lead","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":51000,"max_usd":124000,"period":"year","method":"global_role_cell_scaled_by_country","sample_n":1199},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"CUDA","optional":false},{"name":"DeepSpeed","optional":false},{"name":"Embodied AI","optional":false},{"name":"FSDP","optional":false},{"name":"JAX","optional":false},{"name":"Kubernetes","optional":false},{"name":"LLM","optional":false},{"name":"Megatron-LM","optional":false},{"name":"Multimodal AI","optional":false},{"name":"NCCL","optional":false},{"name":"PyTorch","optional":false},{"name":"Ray","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"RLHF","optional":false},{"name":"SLURM","optional":false},{"name":"TensorFlow","optional":false},{"name":"Vision-Language-Action","optional":false},{"name":"World Models","optional":false}],"status":"live","first_seen_at":"2026-03-12T02:43:41Z","employer_posted_date":"2026-10-03","last_verified_at":"2026-10-22T13:25:28Z","board_verified":true,"closed_at":null,"days_open":224,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":224},"description":"岗位职责 / Responsibilities\n职位背景\n我们正在建设一个面向 具身智能（Embodied AI）与机器人学习 的大规模研究中心，拥有 大规模 GPU 集群与真实机器人数据闭环。团队致力于研发 多模态大模型（Multimodal Foundation Model）、VLA（Vision-Language-Action）、强化学习（Reinforcement Learning）与世界模型（World Model） 等核心技术。\n我们在招聘 ML Infrastructure Lead，负责设计和建设支持大规模模型训练的 机器学习平台与分布式训练基础设施，包括 训练系统、GPU 集群调度、实验平台与数据训练 pipeline，以支持研究团队在大规模计算环境下高效进行模型训练与算法迭代。\n工作职责\n负责机器学习基础设施与训练平台的架构设计与建设\n设计并维护 大规模 GPU 集群训练系统（H100/H200 等）\n构建支持 大模型（LLM / Multimodal / VLA） 的分布式训练系统\n搭建 训练 pipeline（dataset → preprocessing → training → evaluation → deployment）\n设计和实现 实验管理系统（Experiment Tracking）、模型版本管理（Model Registry）\n优化 GPU 利用率、通信效率与训练稳定性\n与研究团队合作支持 大模型训练、强化学习训练与多模态模型训练\n与机器人系统团队合作，实现模型 推理部署（Inference / Serving）\n组建并领导 ML Infrastructure 团队\n任职要求 / Requirements\n任职要求\n计算机、人工智能或相关专业 硕士及以上学历\n5年以上机器学习工程或 AI 平台经验\n熟悉主流深度学习框架：PyTorch / JAX / TensorFlow\n熟悉分布式训练技术：FSDP / Megatron / DeepSpeed / Horovod\n熟悉 GPU 集群与训练调度系统：Slurm / Kubernetes / Ray\n熟悉机器学习训练 pipeline 与数据系统：dataset pipeline / experiment tracking / model registry\n熟悉 GPU 计算优化：CUDA / NCCL / mixed precision / memory optimization\n具备良好的系统架构能力与团队协作能力\n加分项\n有大模型训练（LLM / Multimodal Foundation Model） 经验\n有强化学习（RL / RLHF / Offline RL） 训练平台经验\n有自动驾驶 ML Infra 或 AI 平台团队经验\n有管理 数百至上千 GPU 集群训练任务 的经验\n有构建 AI Training Platform / ML Platform 的经验","description_format":"text","description_chars":1253,"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":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Robotics AI","Robotic Software & Control Systems","Humanoid Robots"],"lifecycle":[{"event":"open","at":"2026-10-03T17:21:24Z"}],"visa":[],"liveness":{"score":35,"band":"fade","label":"Fading","p_open":1,"p_active":0.795,"p_room":0.44,"age_days":224,"expected_fill_days":204,"reasons":["conf:0","velocity","win:tail","crowd:brand"],"computed_at":"2026-10-22T06:10:10Z"},"pay":null,"html_url":"https://alion.io/job/agibot-ai-infrastructure-lead","json_url":"https://alion.io/job/agibot-ai-infrastructure-lead.json","meta":{"generated_at":"2026-10-22T15:05:19Z","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":14618,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-23T00:00:00Z"}},"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":65142},"rest":"https://alion.io/mcp/rest/get_company?id=65142"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fagibot-ai-infrastructure-lead"},{"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%2Fagibot-ai-infrastructure-lead"},{"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%2Fagibot-ai-infrastructure-lead"},{"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/agibot-ai-infrastructure-lead\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fagibot-ai-infrastructure-lead"}]}