{"id":1390451,"url":"https://alion.io/job/xiaopeng-ai-infra-engineeragentic-runtime","title":"AI Infra Engineer（Agentic Runtime）","company":{"id":1822489,"name":"XPeng","domain":"xiaopeng.com","url":"https://alion.io/company/xiaopeng-com","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":1001,"ghost_share":0.291,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":128,"computed_at":"2026-10-17T05:46:00Z"}},"role":"DevOps","role_family":"DevOps","seniority":null,"employment_type":"full_time","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":"CUDA Toolkit","optional":false},{"name":"Isaac Lab","optional":false},{"name":"Isaac Sim","optional":false},{"name":"Kubernetes","optional":false},{"name":"Linux","optional":false},{"name":"MuJoCo","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"PyTorch C++","optional":false},{"name":"Ray","optional":false},{"name":"SGLang","optional":false},{"name":"Triton","optional":false},{"name":"vLLM","optional":false}],"status":"live","first_seen_at":"2026-09-14T10:28:22Z","employer_posted_date":"2026-09-28","last_verified_at":"2026-10-17T15:06:23Z","board_verified":true,"closed_at":null,"days_open":33,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":32},"description":"岗位职责 / Responsibilities\n参与从 0 到 1 建设具身学习基础设施平台，为机器人大模型的强化学习后训练、评测与自迭代提供统一的环境服务与策略推理能力。以仿真环境和策略推理为切入点，通过资源调度、系统性能优化和运行保障，提高有效样本产出，降低实验等待与资源成本，并逐步扩展至端侧和真机执行场景。\n职位描述\n1. 环境与 Rollout 服务平台建设：建设共享 Sandbox 资源池与执行服务，实现环境申请、初始化、隔离、重置、回收与运行观测; 对接强化学习训练框架，支撑真实具身模型训练与评测任务; \n2. 策略推理集成与优化：集成和优化 vLLM、SGLang 等推理引擎，建设策略服务部署、路由与资源管理能力; 结合业务负载优化批处理、缓存、多模态处理与模型执行效率，保障权重更新与模型版本关联的正确性; \n3. 资源画像与动态调度：根据任务类型、环境资产和实际资源用量建立资源画像，设计预热、资产亲和、配额管理与动态扩缩容策略，通过运行反馈持续优化资源申请规格、并发配置与调度效率; \n4. 端到端性能分析：分析环境准备、仿真执行、观测传输、策略推理及权重同步等阶段的瓶颈，建立可复现的性能基线，以有效 Rollout 吞吐、端到端时延和资源成本验证优化收益; \n5. 稳定性与执行正确性保障：完善故障检测、超时处理、背压、恢复与资源清理机制，支持长时间无人值守运行; 建立任务、环境、轨迹、Reward 与 Policy 版本的关联追溯，保障执行隔离与样本正确性; \n6. 标准化接入与架构演进：设计可扩展的任务与 Runtime 接口，支持 Isaac Sim、Unity 等仿真环境，以及强化训练、评测、Replay 等业务复用平台能力，为后续边缘节点、台架和机器人接入奠定基础。\n任职要求 / Requirements\n1. 扎实的 Python 编程与软件工程能力，熟悉 C++ / Go 至少一门，熟悉并发、异步、网络通信及 Linux 系统，能够独立定位复杂系统问题; \n2. 有分布式平台或计算服务研发经验，熟悉 Kubernetes、Ray 等技术中的至少一种，理解资源调度、服务生命周期、状态管理和故障恢复; \n3. 熟悉大模型或多模态模型推理流程，具有 vLLM、SGLang 或同类推理系统的部署、集成或性能优化经验; \n4. 具备系统性能分析能力，能够结合 CPU、GPU、内存、网络及应用链路数据定位瓶颈，并通过对照测试验证收益; \n5. 了解强化学习系统中训练、Rollout、环境交互和权重同步的关系，能够与算法团队共同保障采样与训练链路的正确性; \n6. 有可维护、可观测的平台服务建设经验，能够从实际业务需求出发完成设计、开发、上线及持续优化。\n加分项\n1. 有 AReaL、verl、RLinf 等强化学习框架的使用、集成或开发经验; \n2. 有 Isaac Sim、Isaac Lab、Unity、MuJoCo 等机器人仿真或云游戏平台相关经验; \n3. 熟悉 PyTorch Profiler、Nsight Systems、Nsight Compute，或具备 CUDA、Triton、CUDA Graph、算子及通信优化经验; \n4. 有 GPU 资源池、异构计算、云边协同、端侧模型部署或真机任务执行系统的建设经验。","description_format":"text","description_chars":1395,"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":[],"lifecycle":[{"event":"open","at":"2026-09-28T11:28:13Z"}],"visa":[],"liveness":{"score":87,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.873,"p_room":1,"age_days":32,"expected_fill_days":128,"reasons":["conf:0","velocity","win:early","comp:brand"],"computed_at":"2026-10-17T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/xiaopeng-ai-infra-engineeragentic-runtime","json_url":"https://alion.io/job/xiaopeng-ai-infra-engineeragentic-runtime.json","meta":{"generated_at":"2026-10-17T17:11:28Z","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":23670,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-18T00:00:00Z"}},"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":1822489},"rest":"https://alion.io/mcp/rest/get_company?id=1822489"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fxiaopeng-ai-infra-engineeragentic-runtime"},{"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%2Fxiaopeng-ai-infra-engineeragentic-runtime"},{"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%2Fxiaopeng-ai-infra-engineeragentic-runtime"},{"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/xiaopeng-ai-infra-engineeragentic-runtime\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fxiaopeng-ai-infra-engineeragentic-runtime"}]}