{
  "$schema": "https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json",
  "basics": {
    "name": "Ying Xiang Zhao",
    "label": "DevOps Engineer",
    "url": "https://geminixiang.com/about/",
    "summary": "DevOps & Backend Engineer with 4+ years across GCP / AWS infrastructure, Kubernetes, Terraform IaC, large-scale data pipelines, ML / LLM model serving and AI agent infrastructure. Currently at GliaCloud running 10 GKE clusters and 200+ serverless services.",
    "email": "contact@geminixiang.com",
    "location": {
      "city": "Taipei",
      "countryCode": "TW"
    },
    "profiles": [
      {
        "network": "GitHub",
        "url": "https://github.com/geminixiang",
        "username": "geminixiang"
      },
      {
        "network": "LinkedIn",
        "url": "https://linkedin.com/in/geminixiang/",
        "username": "geminixiang"
      },
      {
        "network": "Cake",
        "url": "https://www.cake.me/geminixiang",
        "username": "geminixiang"
      },
      {
        "network": "Website",
        "url": "https://geminixiang.com",
        "username": "geminixiang"
      }
    ]
  },
  "work": [
    {
      "name": "集雅科技 GliaCloud",
      "position": "DevOps & Backend Engineer",
      "url": "https://www.gliacloud.com",
      "startDate": "2023-02",
      "highlights": [
        "[Infrastructure] 主導 IaC 實踐，採用 Terraform (Terramate) 維護公司所有雲端基礎建設，並以 AI Agent 加速審核與建置流程，大幅節省人力成本",
        "[Infrastructure] 建構大規模用戶資料收集系統，每月處理 3,000 億次請求，涵蓋 Load Balancer、GKE、Cloud Logging、Cloud Storage、BigQuery 完整資料處理 pipeline",
        "[Infrastructure] 管理 10 個 GKE cluster、200+ 個 serverless service，確保系統高可用與穩定性",
        "[AI Agent Infrastructure] 主導 mikan agent 導入，降低使用門檻，輔助公司運維及管理、系統偵錯自動化、產品進度管理與即時資料查詢",
        "[SaaS Operations] 管理 SaaS 專案完整雲端架構：Cloud Run、Cloud SQL、Memorystore for Redis、API Gateway",
        "[SaaS Operations] 優化對外 API 安全機制，強化身份驗證與存取控管",
        "[Performance] 定位 DB slow query 根因，將隨資料量線性增長的 API 回應時間從數分鐘壓縮至 3 秒內",
        "[Performance] 針對高併發場景重構 ML 任務批次寫入機制，提升系統吞吐量數倍",
        "[ML Model Deployment] 部署並維運多套 LLM 推論服務（自行 fine-tune 語言模型、開源 video / image 生成模型），依服務世代採 PyTorch Serve / NVIDIA Triton / BentoML 三套維運策略，並維護 HuggingFace、Replicate 上的實驗性部署流程",
        "[ML Model Deployment] 在 Azure NVIDIA A10 GPU VM 上建置並維運 NVIDIA Omniverse 基礎設施，支援 3D 場景生成與 AI 視覺內容研究"
      ]
    },
    {
      "name": "鈊象電子 IGS",
      "position": "Backend & DevOps Engineer",
      "startDate": "2022-03",
      "endDate": "2023-02",
      "highlights": [
        "負責遊戲營運後台 API 開發與系統整合，建構模組化工具框架支援業務資料管理",
        "運用 AWS EC2、Amazon MSK、AWS Lambda、Amazon Bedrock 建構雲端服務與資料流處理架構",
        "設計並維護 Jenkins CI/CD pipeline，提升部署效率與穩定性",
        "與台灣科技大學（NTUST）產學合作，設計遊戲日誌即時資料處理框架"
      ]
    },
    {
      "name": "博錸生技",
      "position": "Frontend Intern",
      "startDate": "2018-08",
      "endDate": "2018-10",
      "highlights": [
        "執行官網全站 RWD 改版（ASP.NET），提升頁面載入速度與行動裝置體驗"
      ]
    }
  ],
  "projects": [
    {
      "name": "mikan",
      "type": "open source",
      "url": "https://github.com/geminixiang/mikan",
      "description": "Self-hosted AI coding agent for organizations: every Slack channel and DM gets its own sandboxed workspace, credentials and memory; also speaks Telegram, Discord and GitHub.",
      "highlights": [
        "Built on pi-agent-core with a unified sandbox execution layer for Docker and Kubernetes Agent Sandbox",
        "Workload isolation through Kata microVMs; conversation-scoped resource and credential boundaries, mount-collision protection, resource limits, idle cleanup and state reconciliation",
        "Deployed to GKE and k3s with Helm; adopted internally at GliaCloud for ops, debugging automation and data queries"
      ],
      "keywords": [
        "TypeScript",
        "Docker",
        "Kubernetes",
        "Helm",
        "Kata Containers"
      ],
      "website": "https://mikan.geminixiang.com"
    },
    {
      "name": "tiny-agent",
      "type": "open source",
      "url": "https://github.com/geminixiang/tiny-agent",
      "description": "Minimal AI coding agents implemented side by side in TypeScript, Go, Python and Rust, with a Traditional Chinese book explaining how coding agents work.",
      "highlights": [
        "Each runtime calls OpenRouter, runs bash / read / write / edit tools, and loads AGENTS.md and skills",
        "Supports MCP, session resume, context compaction, usage / cache accounting and cancellation",
        "Default model chosen from a cross-runtime eval of speed, stability, convergence and token efficiency"
      ],
      "keywords": [
        "TypeScript",
        "Go",
        "Python",
        "Rust"
      ],
      "website": "https://tiny-agent.geminixiang.com"
    },
    {
      "name": "SentriPay",
      "url": "https://sentripay.com",
      "description": "Travel expense splitter I run: multi-currency conversion, no app to install, and a shareable link that keeps everyone's trip ledger in sync."
    },
    {
      "name": "Studio",
      "url": "https://studio.geminixiang.com",
      "description": "Browser-based video editor built on WebCodecs."
    }
  ],
  "education": [
    {
      "institution": "國立政治大學 National Chengchi University",
      "studyType": "Master's, Library & Information Science",
      "startDate": "2019",
      "endDate": "2021"
    },
    {
      "institution": "國立臺北科技大學 National Taipei University of Technology",
      "studyType": "Bachelor's, Computer Science",
      "startDate": "2014",
      "endDate": "2018"
    }
  ],
  "skills": [
    {
      "name": "DevOps / Cloud",
      "keywords": [
        "GCP",
        "AWS",
        "Cloudflare",
        "Terraform / CDKTF",
        "Kubernetes",
        "Docker",
        "Cloud Build",
        "GitHub Actions",
        "ELK Stack",
        "SonarQube",
        "Linux",
        "Git"
      ]
    },
    {
      "name": "Backend",
      "keywords": [
        "Python",
        "Express",
        "Bash",
        "MongoDB",
        "PostgreSQL",
        "MySQL",
        "Redis",
        "RabbitMQ",
        "Kafka",
        "Spark"
      ]
    },
    {
      "name": "ML / AI",
      "keywords": [
        "PyTorch Serve",
        "NVIDIA Triton",
        "BentoML",
        "HuggingFace",
        "Replicate",
        "AI agents"
      ]
    },
    {
      "name": "Frontend",
      "keywords": [
        "Vue",
        "React",
        "Astro"
      ]
    }
  ],
  "languages": [
    {
      "language": "Mandarin (native)"
    },
    {
      "language": "English"
    }
  ],
  "meta": {
    "canonical": "https://geminixiang.com/resume.json",
    "openToWork": {
      "roles": [
        "DevOps Engineer",
        "Platform Engineer",
        "Site Reliability Engineer",
        "AI Infrastructure Engineer"
      ],
      "locations": [
        "Taipei, Taiwan",
        "Remote"
      ],
      "contact": [
        {
          "name": "Email",
          "url": "mailto:contact@geminixiang.com"
        },
        {
          "name": "Cake",
          "url": "https://www.cake.me/geminixiang"
        },
        {
          "name": "LinkedIn",
          "url": "https://linkedin.com/in/geminixiang/"
        }
      ],
      "note": "目前開放新的工作機會（open to work），歡迎來信 contact@geminixiang.com 或透過 Cake / LinkedIn 聯繫。"
    }
  }
}