锦鲤求职岗位描述
Job Description:
本岗位负责公司人工智能及大语言模型（LLM）相关安全工具的日常运维工作，保障安全系统的稳定、高效与安全运行，并持续优化运维流程与响应机制。
This role is responsible for the day-to-day operations of security tools related to artificial intelligence and large language models (LLMs), ensuring the stability, efficiency, and security of security systems, while continuously improving operational processes and response mechanisms.
Key Responsibilities:
1. 工具部署与配置管理 / Tool Deployment & Configuration Management
a) 负责AI/LLM安全工具的部署、初始化配置及版本升级管理 / Manage the deployment, initial configuration, and version upgrade of AI/LLM security tools
b) 制定并维护配置基线，确保配置项的一致性与可追溯性 / Define and maintain configuration baselines to ensure consistency and traceability of configuration items
2. 系统集成与流程嵌入 / System Integration & Process Embedding
a) 将安全工具与现有CI/CD流水线、监控平台、身份认证系统等进行无缝集成 / Seamlessly integrate security tools with existing CI/CD pipelines, monitoring platforms, and identity authentication systems
b) 推动安全能力嵌入研发与运维流程，实现“安全即代码”与自动化策略实施 / Drive the embedding of security capabilities into R&D and operations workflows, enabling "security as code" and automated policy enforcement
3. 监控、告警与性能优化 / Monitoring, Alerting & Performance Optimization
a) 建立并完善安全工具的监控指标体系，配置合理的告警阈值与通知策略 / Establish and enhance monitoring metric systems for security tools, configure reasonable alert thresholds and notification policies
b) 定期分析系统性能瓶颈，进行容量规划与资源调优，保障高可用性 / Regularly analyze system performance bottlenecks, conduct capacity planning and resource tuning to ensure high availability
4. 工具自身的安全维护 / Security Maintenance of Tools
a) 定期对安全工具自身进行漏洞扫描、安全加固与补丁更新 / Regularly perform vulnerability scanning, security hardening, and patch updates on the security tools themselves
b) 管理工具访问权限，落实最小权限原则，定期审计操作日志 / Manage tool access permissions, enforce the principle of least privilege, and periodically audit operational logs
5. 故障排查与应急响应 / Troubleshooting & Emergency Response
a) 及时响应安全工具的异常告警与故障事件，快速定位根因并实施修复 / Respond promptly to abnormal alerts and incidents of security tools, quickly identify root causes and implement fixes
b) 参与安全事件应急响应流程，配合安全团队进行影响评估与事后复盘 / Participate in security incident emergency response procedures, collaborating with the security team on impact assessment and post-incident reviews
6. 运维文档维护 / Operations Documentation Maintenance
a) 编写并持续更新运维手册、故障处置SOP、架构拓扑图及变更记录 / Write and continuously update operations manuals, fault handling SOPs, architecture topology diagrams, and change records
b) 建立知识库体系，推动运维经验的沉淀与共享 / Establish a knowledge base system to promote the accumulation and sharing of operational experience
Skills and Attributes for Success
1. 计算机、信息安全或相关专业本科及以上学历 / Bachelor’s degree or above in Computer Science, Information Security, or related fields
2. 3年以上运维或安全运维经验，有AI/LLM相关系统维护经验者优先 / 3+ years of experience in operations or security operations; experience with AI/LLM system maintenance is a plus
3. 熟悉Linux系统、容器化（Docker/K8s）、CI/CD工具及常见监控方案（如Prometheus、Grafana）/ Proficient in Linux, containerization (Docker/K8s), CI/CD tools, and common monitoring solutions (e.g., Prometheus, Grafana)
4. 掌握至少一种脚本语言（Python/Shell），具备自动化运维能力 / Skilled in at least one scripting language (Python/Shell) with automation capabilities
5. 了解大语言模型基础架构及常见安全风险（如提示注入、数据泄露等）者加分 / Knowledge of LLM architecture and common security risks (e.g., prompt injection, data leakage) is an advantage
6. 具备良好的问题分析能力、沟通能力及文档撰写能力 / Strong problem-solving, communication, and documentation skills