System Operations Engineer (AI Infrastructure)

Job Overview

Responsible for daily operation and maintenance of computing power platform, deployment & maintenance of large models, and operation & maintenance of knowledge base system. Focus on adaptation and execution of computing power platform, maintenance of computing power environment and system inspection to ensure stable operation of AI infrastructure.

职位概述

负责算力平台的日常运维、大模型部署维护和知识库系统运维工作。侧重算力平台适配执行、算力环境维护和系统巡检，保障AI基础设施的稳定运行。

Key Responsibilities

— 1 Responsible for daily monitoring, inspection and troubleshooting of the department’s computing clusters and GPU/NPU servers.

— 2 Participate in deployment, adaptation verification and environment maintenance of large language models on Huawei Ascend platform.

— 3 Participate in daily operation and maintenance and data update of the local knowledge base system.

— 4 Responsible for installation, configuration, version upgrade of third-party computing software and user technical support.

— 5 Participate in setup and maintenance of POC test environment for technical evaluation.

— 6 Compile operation & maintenance technical documents, troubleshooting guides and operation manuals.

主要职责

— 1 负责部门算力集群、GPU/NPU服务器的日常监控、巡检和故障处理

— 2 参与大语言模型在华为昇腾平台上的部署执行、适配验证和环境维护

— 3 参与本地知识库系统的日常运维和数据更新

— 4 负责第三方计算软件的安装配置、版本更新和用户技术支持

— 5 参与技术评估工作中的POC测试环境的搭建和维护

— 6 编写运维技术文档、故障处理指南和操作手册

Qualifications & Skill Requirements

— 1 Master’s degree or above, major in Computer Science and Technology, Software Engineering, Electronic Information or related fields.

— 2 At least 1 year of working experience in Linux system operation and maintenance or related roles.

— 3 Proficient in Linux system administration; capable of writing Shell and Python scripts.

— 4 Familiar with Docker container technology, able to deploy applications and perform basic debugging.

— 5 Prior knowledge of basic concepts of large model deployment is preferred.

— 6 Willing to spend time learning and practicing on Huawei Ascend platform.

— 7 Strong job stability, sense of responsibility and problem troubleshooting capabilities.

— 8 Good habits in documentation writing and service awareness.

任职资格与技能要求

— 1 硕士及以上学历，计算机科学与技术、软件工程、电子信息或相关专业

— 2 具有一年及以上Linux系统运维或相关工作经验

— 3 熟练掌握Linux系统管理，具备Shell和Python脚本编写能力

— 4 了解Docker容器化技术，能够完成应用部署和基本调试

— 5 了解大模型部署的基本概念者优先

— 6 愿意在华为昇腾平台上投入时间学习和实践

— 7 具有较强的工作稳定性、责任心和问题排查能力

— 8 具有良好的文档编写习惯和服务意识