riotpiao.com/lib/translations.json

{
  "en": {
    "header": {
      "title": "Rock Liang",
      "subtitle": "Senior Software Engineer",
      "nav": {
        "home": "Home",
        "askPoimen": "AskPoimen",
        "skills": "Skills",
        "contact": "Contact"
      },
      "experience": "Experience",
      "experienceValue": "6+ YoE",
      "education": "Education",
      "educationValue": "M.Sc. UOttawa",
      "educationDetails": {
        "bachelor": {
          "school": "University of Ottawa",
          "degree": "Bachelor's Degree, Computer Science",
          "period": "2016 – 2019"
        },
        "master": {
          "school": "University of Ottawa",
          "degree": "Master's degree, Computer Science",
          "period": "Sep 2019 – Nov 2021",
          "publication": {
            "title": "Additive Depth Maps for Real-Time Rendering",
            "venue": "VIVA Lab, University of Ottawa",
            "url": "https://www.site.uottawa.ca/school/research/viva/projects/additive-depth-maps/index.html"
          }
        }
      },
      "contact": {
        "portfolio": "portfolio.riotpiao.com",
        "github": "GitHub",
        "privateGithub": "Private Github",
        "linkedin": "LinkedIn",
        "email": "Email",
        "copy": "Copy"
      },
      "skills": {
        "infrastructure": {
          "title": "Infrastructure",
          "items": [
            "Kubernetes",
            "Talos",
            "ArgoCD",
            "Terraform",
            "Docker",
            "OpenShift"
          ]
        },
        "cloud": {
          "title": "Cloud & Distributed",
          "items": [
            "AWS",
            "DynamoDB",
            "CloudWatch",
            "gRPC",
            "Cloudflare"
          ]
        },
        "languages": {
          "title": "Languages",
          "items": [
            "Go",
            "Java",
            "Python",
            "C++",
            "TypeScript"
          ]
        },
        "data": {
          "title": "Data & Messaging",
          "items": [
            "Kafka",
            "PostgreSQL",
            "Temporal",
            "Redis"
          ]
        },
        "aiml": {
          "title": "AI/ML",
          "items": [
            "vLLM",
            "PyTorch",
            "Ollama",
            "KServe"
          ]
        },
        "observability": {
          "title": "Observability",
          "items": [
            "Prometheus",
            "Grafana",
            "Loki",
            "OpenTelemetry"
          ]
        }
      }
    },
    "hero": {
      "title": "Senior Software Engineer",
      "subtitle": "Infrastructure × Backend × LLM Systems",
      "description": "Building observable, scalable, fault-tolerant systems for mass audience.",
      "exploreMore": "About Rock",
      "terminalHint": "Press",
      "terminalHintSuffix": "to explore via terminal",
      "roles": [
        "Infrastructure",
        "SRE",
        "SDE",
        "Agentic Engineer",
        "Distributed Systems",
        "System/Platform Engineer"
      ]
    },
    "bio": {
      "title": "About Me",
      "intro": "Senior Software Engineer with 6+ years of experience building observable, scalable, and fault-tolerant systems for mass audiences.",
      "expertise": {
        "title": "Technical Expertise",
        "content": "Infrastructure automation (Terraform, Kubernetes, ArgoCD) • Distributed systems (gRPC, Kafka, AWS Step Functions) • LLM inference optimization (INT4/INT8 quantization) • Backend systems (Go, Java, Python, C++)"
      },
      "highlights": {
        "title": "Career Highlights",
        "items": [
          "Launched AWS Distributed-Map service across 57+ regions",
          "Built multi-region infrastructure at RBC (40% cost reduction)",
          "Architected production homelab: Kubernetes, Kafka, LLM inference",
          "Poimen: Agent workflow orchestration + Graph-RAG memory system"
        ]
      },
      "educationTitle": "Education",
      "educationContent": "M.Sc. Computer Science, University of Ottawa (2019–2021)\nB.Sc. Computer Science, University of Ottawa (2016–2019)",
      "currentFocus": "Currently focused on infrastructure automation, LLM systems optimization, and building the next generation of distributed systems."
    },
    "projects": {
      "title": "What have i Built and Building",
      "subtitle": "Demonstrate my work",
      "watchVideo": "Watch Video",
      "readArticle": "Read Article",
      "askPoimen": "Ask Poimen for technical details",
      "items": [
        {
          "title": "Poimen: Agent Workflow Orchestration",
          "description": "Poimen (Greek: Ποιμήν) means \"shepherd\" — a guide who tends, orchestrates, and reconciles. Poimen is an intelligent orchestration layer that transforms natural language into durable, distributed agent workflows powered by Temporal.",
          "longDescription": "An LLM router analyzes user intent, retrieves relevant knowledge from semantic memory, and generates executable workflow specs — enabling agent deployment at scale where any activity can be wired as a composable step in the reconciliation pipeline. Every workflow is durable, retryable, and observable.",
          "stat": "Temporal, LLM Routing, 9 Composable Activities",
          "highlight": "Natural language → executable WorkflowSpec via reasoning model + memory-augmented context retrieval + durable state machine execution.",
          "bullets": [
            "LLM-Powered Workflow Routing: Natural language → executable WorkflowSpec via reasoning model (api.riotpiao.com). Activity Knowledge Base (9 activities) informs the LLM about timeouts, retry policies, and dependencies—intelligent step ordering and error handling strategies.",
            "Memory-Augmented Context Retrieval: RetrieveMemoryActivity queries poimen-memory (Rust semantic search service) for relevant skills and lessons before routing—injecting domain knowledge into prompts for context-aware workflow generation.",
            "Generic State Machine Executor: RoutingWorkflow executes any JSON workflow spec with JSONPath parameter chaining (${Step1.output.path}), automatic retries for flaky activities, catch blocks for error recovery, and Temporal's durable execution guarantees—every registered activity a composable building block."
          ]
        },
        {
          "title": "Poimen Memory System",
          "description": "The memory layer behind Poimen — a distributed Graph-RAG system that gives the shepherd long-term recall, semantic search, and hierarchical access control over its knowledge base.",
          "longDescription": "Three-tier context retrieval pipeline with PageRank-style link scoring, hybrid search fusion (HNSW + BM25), and OIDC-based access control for multi-tenant knowledge graphs.",
          "stat": "Graph-RAG, pgvector, OpenSearch, Rust + Actix-web",
          "highlight": "Bidirectional wiki-link indexing with RRF fusion + hierarchical RBAC — 50ms signature match tier, graph-boosted hybrid search tier, Obsidian fallback.",
          "bullets": [
            "Graph-RAG with Wiki-Link Indexing (Rust, pgvector, OpenSearch): Built bidirectional link graph from [[wiki-link]] syntax during ingestion. PageRank-style score propagation boosts linked documents' relevance. RRF fusion merges HNSW cosine (pgvector) + BM25 lexical (OpenSearch). WikiScopedFilter constrains traversal to project boundaries.",
            "Three-Tier Context Retrieval (Actix-web, tokio): Async pipeline — Tier 1: MD5 signature match (<50ms), Tier 2: graph-boosted hybrid search with link-distance decay, Tier 3: Obsidian API fallback. Budget-aware assembly drops lower tiers first. Shingle-based Jaccard deduplication (>0.5) prevents redundant chunks.",
            "Hierarchical RBAC (Authentik OIDC, JWT, Kubernetes): Role → AccessRule[] → AccessScope model with project/visibility/owner/group constraints. JWT roles claim maps to YAML rules; AccessGuard.filter_resources() applies post-retrieval filtering. Dual-write indexer (eventual consistency via queue) maintains RBAC-aware views. SOPS/age encryption, ArgoCD deployment."
          ]
        },
        {
          "title": "Homelab: Production-Grade Kubernetes Platform",
          "description": "From bare metal to a self-healing, GitOps-driven platform — 4-node cluster running 20+ services with full observability, zero-trust networking, and GPU-accelerated AI inference.",
          "longDescription": "Built and operate a production-grade Kubernetes platform on Talos Linux — self-healing nodes, declarative GitOps deployments via ArgoCD, SOPS-encrypted secrets, OIDC single sign-on, and end-to-end observability (Prometheus → Grafana → Loki → Tempo). Every change is auditable, every failure auto-recovers, every service is monitored.",
          "stat": "4 nodes · 20+ services · 99.2% uptime · 0 manual deployments",
          "highlight": "Production-grade platform engineering — not a hobby cluster. Self-healing infrastructure, GitOps-only deployments, full-stack observability, and GPU inference at home.",
          "bullets": [
            "Talos Linux bare-metal cluster — immutable OS, API-driven node management, self-healing on failure",
            "ArgoCD + Kustomize + SOPS — zero-touch GitOps: every deploy is a git commit, every secret is encrypted",
            "Authentik OIDC SSO + RBAC — single identity across 20+ services, zero-trust access from day one",
            "Prometheus + Grafana + Loki + Tempo — full observability stack: metrics, logs, traces, alerts",
            "vLLM GPU inference (Qwen3-32B) + KServe — production AI serving with autoscale and traffic splitting",
            "Temporal + Kafka + CloudNativePG — durable workflows, event streaming, HA PostgreSQL with pgvector",
            "Cloudflare Tunnel + cert-manager — zero-trust ingress, auto-TLS, no exposed ports"
          ],
          "deepDive": {
            "label": "Explore the Architecture →",
            "url": "/homelab"
          }
        },
        {
          "title": "RBC: Multi-Cloud Platform",
          "description": "Unified infrastructure platform consolidating public cloud and on-prem.",
          "longDescription": "Terraform automation with Temporal orchestration. 99.2% automated provisioning, notification-driven operator fallback.",
          "stat": "200+ microservices, 4 regions, 2hr→20min deploy",
          "highlight": "Standardized IaC patterns across 12 teams—cut provisioning toil, 3x integration velocity.",
          "bullets": [
            "Integrated Terraform Cloud to centralize IaC workflows—reduced onboarding time for 12 teams",
            "Built K8s CronJob to detect and reconcile Terraform state drift automatically (Golang)",
            "Designed Slack notification service with Golang workers—operators resolve apply failures in <5min",
            "Led requirement gathering across 4 platform teams—disambiguated specs, unblocked 3 stalled projects",
            "Translated technical decisions for non-technical stakeholders—secured buy-in for platform migration"
          ],
          "deepDive": {
            "label": "Deep Dive: Terraform State Drift Solution →",
            "url": "/terraform-drift"
          }
        },
        {
          "title": "AWS Distributed-Map",
          "description": "Launched distributed task orchestration service for mission-critical workloads.",
          "longDescription": "Optimized execution across 57+ regions with fault-tolerant scheduling and auto-scaling.",
          "stat": "57+ regions, sub-100ms P99, 20x burst traffic",
          "highlight": "Introduced JSON state input for larger payloads—unlocked new customer use cases.",
          "bullets": [
            "Under tight deadline, introduced separate state in Map vs new functions—simplified customer adoption (Java)",
            "Built checkpoint recovery for mid-workflow failures—customers resume without full re-run",
            "Solved distributed edge cases: race conditions, concurrent updates, dependent service failures, message deduplication",
            "Owned oncall for the service—built CloudWatch dashboards, wrote runbooks, debugged production live"
          ]
        }
      ]
    },
    "experience": {
      "title": "Explore Experience",
      "subtitle": "Feel free to Ask Poimen more abt it",
      "items": [
        {
          "company": "Poimen (Ποιμήν)",
          "role": "Architect / Agentic Engineer",
          "period": "May 2025 — Present",
          "description": "Poimen (\"shepherd\" in Greek) — a self-learning agent platform with two pillars:\n\n🧠 <b>Memory</b>: <b>Rust</b>-based <b>Graph-RAG</b> service. Fixed-window chunking → <b>TEI</b> embeddings → <b>pgvector</b> + bidirectional graph index. Three-tier retrieval via <b>RRF fusion</b>: signature match (<b>50ms</b>), graph-boosted hybrid search, <b>Obsidian</b> fallback. Self-compacting cache evicts stale embeddings and auto-reconciles the graph on every write.\n\n⚡ <b>Workflows</b>: <b>Go</b> + <b>Temporal</b> durable execution engine. LLM router generates <b>WorkflowSpecs</b> from natural language, informed by an <b>Activity Knowledge Base</b> (9 activities with timeout/retry/dependency metadata). <b>JSONPath</b> parameter chaining, catch-block recovery, <b>exactly-once</b> guarantees. <b>Goal-driven</b>: describe intent → platform assembles, executes, and self-heals."
        },
        {
          "company": "riotpiao.com",
          "role": "DevOps / SRE / SDE",
          "period": "May 2025 — Present",
          "description": "Designed and operate a <b>production-grade bare-metal Kubernetes platform</b> from scratch — 4 nodes, <b>3 control planes</b>, <b>20+ services</b>, <b>99.2% uptime</b>.\n\n🏗️ <b>Infrastructure</b>: <b>Talos Linux</b> immutable OS, <b>etcd</b> distributed consensus, <b>Longhorn</b> block storage, <b>MinIO</b> S3, <b>CloudNativePG</b> with <b>pgvector</b>. Resolved etcd leader election failures caused by 200ms network latency — re-architected the physical topology for sub-5ms RTT.\n\n🔄 <b>GitOps & CI/CD</b>: Evolved from pure <b>Terraform</b> to <b>Terraform</b> (node provisioning) + <b>ArgoCD</b> (application delivery). <b>Kustomize</b> overlays, <b>SOPS</b>-encrypted secrets, <b>Forgejo CI</b> with DinD runners. Zero manual deployments — every change is a git commit.\n\n🔐 <b>Security & Identity</b>: <b>Authentik OIDC SSO</b> + <b>RBAC</b> across all services. <b>Cloudflare Tunnel</b> zero-trust ingress, <b>cert-manager</b> auto-TLS, no exposed ports.\n\n📊 <b>Observability</b>: <b>Prometheus</b> + <b>Grafana</b> + <b>Loki</b> + <b>Tempo</b> — full metrics, logs, traces, and alerting stack.\n\n🤖 <b>AI/ML Serving</b>: <b>vLLM</b> GPU inference (<b>Qwen3-32B</b>), <b>KServe</b> model orchestration, <b>TEI</b> embeddings, <b>Ollama</b> lightweight models."
        },
        {
          "company": "RBC",
          "role": "Lead Software Engineer",
          "period": "Nov 2024 — May 2026",
          "description": "Led infrastructure platform engineering for multi-cloud IaC across <b>12 teams</b>.\n\n🏗️ <b>State Migration</b>: Migrated <b>500+ Terraform</b> resource state files from S3 to <b>JFrog Artifactory</b>. Split plan/apply into <b>immutable artifact pipeline</b> with throttled parallelism — eliminated <b>503 timeouts</b>, lock contention, and <b>zero state corruption</b> post-migration.\n\n🔍 <b>Drift Detection</b>: Built nightly <b>cron-based drift detection</b> with <b>Slack</b> alerting — cut configuration drift visibility from <b>3 weeks → &lt;24 hours</b>. Stopped engineers hotfixing in cloud console without updating code.\n\n⚡ <b>Workflow Orchestration</b>: Introduced <b>Temporal</b> for durable workflow execution across provisioning pipelines. Standardized <b>IaC patterns</b> across teams — <b>3× integration velocity</b>.\n\n<b>Stack</b>: <b>Terraform</b>, <b>OpenShift</b>, <b>Docker</b>, <b>Golang</b>, <b>Grafana</b>, <b>Artifactory</b>, <b>Temporal</b>"
        },
        {
          "company": "AWS",
          "role": "Senior Software Engineer (Step Functions)",
          "period": "2022 — 2024",
          "description": "Owned <b>Distributed-Map</b> end-to-end for <b>AWS Step Functions</b> — <b>57+ regions</b>, <b>sub-100ms P99</b> latency.\n\n🚀 <b>Feature Ownership</b>: Launched <b>Redrive Execution</b> — retry-from-failure-point for distributed workflows. Designed <b>JSON state input</b> for larger payloads, unlocking new customer use cases. Caught a breaking <b>condition field change</b> in code review — coordinated simultaneous frontend + backend deployment to prevent customer impact.\n\n📊 <b>Operational Excellence</b>: Built <b>CloudWatch</b> dashboards, authored runbooks, owned <b>oncall rotation</b>. Maintained <b>backward compatibility</b> across frontend/backend release cycles.\n\n🔧 <b>Distributed Systems</b>: <b>DynamoDB</b> partition design, <b>gRPC</b> service mesh, <b>disaster recovery</b> planning, <b>multi-region</b> replication.\n\n<b>Stack</b>: <b>Java</b>, <b>AWS</b>, <b>DynamoDB</b>, <b>CloudWatch</b>, <b>gRPC</b>, <b>Step Functions</b>"
        },
        {
          "company": "Titus",
          "role": "Software Engineer Intern",
          "period": "May — Aug 2019",
          "description": "Data classification security startup — built detection and connector systems.\n\n🔍 <b>Anomaly Detection</b>: Built <b>Personal Data Detection</b> pipeline to flag classified data exfiltration — <b>97.8% accuracy</b>.\n\n⚡ <b>Connector</b>: Fault-tolerant <b>Golang</b> data connector — <b>28% P99 improvement</b> over legacy system.\n\n🔧 <b>Build System</b>: Re-integrated <b>SmartRegex</b> engine with <b>CMake</b> + <b>C++</b> on Linux/Unix — <b>5× faster deployment</b>.\n\n<b>Stack</b>: <b>Golang</b>, <b>C++</b>, <b>CMake</b>, <b>Docker</b>, <b>Linux</b>"
        },
        {
          "company": "NAV Canada",
          "role": "Summer Student",
          "period": "May — Aug 2018",
          "description": "Air traffic control software — enterprise web applications for flight planning and weather briefing.\n\n✈️ <b>FWGS Weather Briefing</b>: Built <b>ReactJS</b> weather briefing interface used by <b>air traffic controllers</b> for real-time flight weather data.\n\n🗳️ <b>NOTAMJ Polls</b>: Developed <b>Django</b> polling application to meet sprint iteration goals within <b>Agile</b> workflow.\n\n📊 <b>Quality</b>: Improved deploy stability with <b>SonarQube</b> code coverage integration on enterprise <b>CFPS</b> platform.\n\n<b>Stack</b>: <b>ReactJS</b>, <b>Django</b>, <b>SonarQube</b>, <b>Agile</b>"
        }
      ]
    },
    "terminal": {
      "title": "Poimen (Agent Terminal)",
      "button": "Ask Poimen",
      "helpText": "type 'help' for commands"
    },
    "footer": {
      "copyright": "© 2025 Rock Liang. Deployed on homelab Kubernetes cluster (4-node Talos).",
      "github": "GitHub",
      "email": "Email"
    }
  },
  "zh": {
    "header": {
      "title": "梁伟哲",
      "subtitle": "高级软件工程师",
      "nav": {
        "home": "首页",
        "askPoimen": "问Poimen",
        "skills": "技能",
        "contact": "联系"
      },
      "experience": "经验",
      "experienceValue": "6年+",
      "education": "学历",
      "educationValue": "渥太华大学硕士",
      "educationDetails": {
        "bachelor": {
          "school": "渥太华大学",
          "degree": "计算机科学学士",
          "period": "2016 – 2019"
        },
        "master": {
          "school": "渥太华大学",
          "degree": "计算机科学硕士",
          "period": "2019年9月 – 2021年11月",
          "publication": {
            "title": "Additive Depth Maps for Real-Time Rendering",
            "venue": "VIVA Lab, University of Ottawa",
            "url": "https://www.site.uottawa.ca/school/research/viva/projects/additive-depth-maps/index.html"
          }
        }
      },
      "contact": {
        "portfolio": "portfolio.riotpiao.com",
        "github": "GitHub",
        "privateGithub": "私人GitHub",
        "linkedin": "领英",
        "email": "邮箱",
        "copy": "复制"
      },
      "skills": {
        "infrastructure": {
          "title": "基础设施",
          "items": [
            "Kubernetes",
            "Talos",
            "ArgoCD",
            "Terraform",
            "Docker",
            "OpenShift"
          ]
        },
        "cloud": {
          "title": "云 & 分布式",
          "items": [
            "AWS",
            "DynamoDB",
            "CloudWatch",
            "gRPC",
            "Cloudflare"
          ]
        },
        "languages": {
          "title": "编程语言",
          "items": [
            "Go",
            "Java",
            "Python",
            "C++",
            "TypeScript"
          ]
        },
        "data": {
          "title": "数据 & 消息",
          "items": [
            "Kafka",
            "PostgreSQL",
            "Temporal",
            "Redis"
          ]
        },
        "aiml": {
          "title": "AI/ML",
          "items": [
            "vLLM",
            "PyTorch",
            "Ollama",
            "KServe"
          ]
        },
        "observability": {
          "title": "可观测性",
          "items": [
            "Prometheus",
            "Grafana",
            "Loki",
            "OpenTelemetry"
          ]
        }
      }
    },
    "hero": {
      "title": "高级软件工程师",
      "subtitle": "基础设施 × 后端 × LLM系统",
      "description": "为大规模用户构建可观测、可扩展、容错的系统。",
      "exploreMore": "关于Rock",
      "terminalHint": "按",
      "terminalHintSuffix": "通过终端探索",
      "roles": [
        "基础设施",
        "SRE",
        "软件开发",
        "AI代理工程师",
        "分布式系统",
        "系统/平台工程师"
      ]
    },
    "bio": {
      "title": "关于我",
      "intro": "拥有6年以上经验的高级软件工程师，专注于为大规模用户构建可观测、可扩展、容错的系统。",
      "expertise": {
        "title": "技术专长",
        "content": "基础设施自动化 (Terraform, Kubernetes, ArgoCD) • 分布式系统 (gRPC, Kafka, AWS Step Functions) • LLM推理优化 (INT4/INT8量化) • 后端系统 (Go, Java, Python, C++)"
      },
      "highlights": {
        "title": "职业亮点",
        "items": [
          "在57+区域发布AWS Distributed-Map服务",
          "在RBC构建多区域基础设施（成本降低40%）",
          "架构生产级家庭实验室：Kubernetes、Kafka、LLM推理",
          "Poimen: 智能体工作流编排 + 图-RAG记忆系统"
        ]
      },
      "educationTitle": "教育背景",
      "educationContent": "渥太华大学计算机科学硕士 (2019–2021)\n渥太华大学计算机科学学士 (2016–2019)",
      "currentFocus": "目前专注于基础设施自动化、LLM系统优化，以及构建下一代分布式系统。"
    },
    "projects": {
      "title": "我构建的项目",
      "subtitle": "展示我的作品",
      "watchVideo": "观看视频",
      "readArticle": "阅读文章",
      "askPoimen": "问Poimen了解技术细节",
      "items": [
        {
          "title": "Poimen: 智能体工作流编排",
          "description": "Poimen（希腊语：Ποιμήν）意为\"牧羊人\"——引导、编排和协调的角色。Poimen 是一个智能编排层，将自然语言转化为由 Temporal 驱动的持久化分布式代理工作流。",
          "longDescription": "LLM路由器分析用户意图，从语义记忆中检索相关知识，生成可执行的工作流规范——实现大规模代理部署，任何活动都可以作为协调管道中的可组合步骤。每个工作流都是持久化的、可重试的、可观测的。",
          "stat": "Temporal, LLM路由, 9个可组合活动",
          "highlight": "自然语言 → 可执行WorkflowSpec：推理模型 + 记忆增强上下文检索 + 持久状态机执行。",
          "bullets": [
            "LLM工作流路由：自然语言 → 可执行WorkflowSpec，通过推理模型。活动知识库（9个活动）告知LLM超时、重试策略和依赖关系——智能步骤排序和错误处理策略。",
            "记忆增强上下文检索：RetrieveMemoryActivity查询poimen-memory（Rust语义搜索服务）获取相关技能和经验——将领域知识注入提示词，实现上下文感知的工作流生成。",
            "通用状态机执行器：RoutingWorkflow执行任何JSON工作流规格，支持JSONPath参数链接、自动重试、catch错误恢复和Temporal持久执行保证——每个注册活动都是可组合的构建块。"
          ]
        },
        {
          "title": "Poimen记忆系统",
          "description": "Poimen 背后的记忆层——分布式 Graph-RAG 系统，为牧羊人提供长期记忆、语义搜索和分层访问控制。",
          "longDescription": "三层上下文检索管道，支持PageRank风格的链接评分、混合搜索融合（HNSW + BM25）和基于OIDC的多租户知识图访问控制。",
          "stat": "图-RAG, pgvector, OpenSearch, Rust + Actix-web",
          "highlight": "双向维基链接索引配RRF融合 + 分层RBAC——50ms签名匹配层、图增强混合搜索层、Obsidian兜底。",
          "bullets": [
            "图-RAG维基链接索引化（Rust、pgvector、OpenSearch）：从[[维基链接]]语法构建双向链接图。PageRank风格评分传播提升链接文档的相关性。RRF融合合并HNSW余弦相似度（pgvector）+ BM25词汇排名（OpenSearch）。WikiScopedFilter将遍历限制在项目边界内。",
            "三层上下文检索（Actix-web, tokio）：异步管道——第1层：MD5签名匹配（<50ms），第2层：图增强混合搜索含链接距离衰减，第3层：Obsidian API兜底。预算感知的响应组装优先丢弃低优先层。基于瓦片的Jaccard去重（>0.5）防止冗余块。",
            "分层RBAC（Authentik OIDC、JWT、Kubernetes）：角色→AccessRule[]→AccessScope模型，包含项目/可见性/所有者/组约束。JWT角色声明映射到YAML规则；AccessGuard.filter_resources()应用检索后过滤。双写索引器（通过队列保证最终一致性）维护RBAC感知视图。SOPS/age加密，ArgoCD部署。"
          ]
        },
        {
          "title": "家庭实验室：生产级 Kubernetes 平台",
          "description": "从裸金属到自愈、GitOps 驱动的平台 — 4节点集群运行20+服务，具备全链路可观测性、零信任网络和GPU加速AI推理。",
          "longDescription": "在 Talos Linux 上构建并运维生产级 Kubernetes 平台 — 自愈节点、ArgoCD 声明式 GitOps 部署、SOPS 加密密钥、OIDC 单点登录，以及端到端可观测性（Prometheus → Grafana → Loki → Tempo）。每次变更可审计，每次故障自动恢复，每个服务均有监控。",
          "stat": "4节点 · 20+服务 · 99.2%可用性 · 0次手动部署",
          "highlight": "生产级平台工程 — 不是业余集群。自愈基础设施、纯GitOps部署、全栈可观测性、家庭GPU推理。",
          "bullets": [
            "Talos Linux 裸金属集群 — 不可变OS、API驱动节点管理、故障自愈",
            "ArgoCD + Kustomize + SOPS — 零接触GitOps：每次部署即git提交，每个密钥均加密",
            "Authentik OIDC SSO + RBAC — 20+服务单一身份，零信任访问",
            "Prometheus + Grafana + Loki + Tempo — 全链路可观测：指标、日志、追踪、告警",
            "vLLM GPU推理 (Qwen3-32B) + KServe — 生产级AI服务，自动扩缩与流量分割",
            "Temporal + Kafka + CloudNativePG — 持久化工作流、事件流、高可用PostgreSQL + pgvector",
            "Cloudflare Tunnel + cert-manager — 零信任入口、自动TLS、无暴露端口"
          ],
          "deepDive": {
            "label": "探索架构详情 →",
            "url": "/homelab"
          }
        },
        {
          "title": "RBC: 多云平台",
          "description": "统一基础设施平台，整合公有云和本地部署。",
          "longDescription": "Terraform自动化配合Temporal编排。99.2%自动化配置，通知驱动的运维人员兜底。",
          "stat": "200+微服务，4个区域，部署2小时→20分钟",
          "highlight": "标准化12个团队的IaC模式——减少配置负担，集成速度提升3倍。",
          "bullets": [
            "集成Terraform Cloud实现IaC工作流集中化——12个团队onboarding时间缩短",
            "构建K8s CronJob自动检测和修复Terraform状态漂移（Golang）",
            "设计Slack通知服务 + Golang worker——运维人员<5分钟解决apply失败",
            "主导4个平台团队需求收集——澄清规格，解锁3个停滞项目",
            "向非技术stakeholder翻译技术决策——获得平台迁移支持"
          ],
          "deepDive": {
            "label": "深入了解：Terraform状态漂移解决方案 →",
            "url": "/terraform-drift"
          }
        },
        {
          "title": "AWS Distributed-Map",
          "description": "发布面向关键任务的分布式任务编排服务。",
          "longDescription": "在57+区域优化执行，具有容错调度和自动扩展功能。",
          "stat": "57+区域，P99延迟<100ms，20x流量突发",
          "highlight": "引入JSON状态输入支持更大负载——解锁新客户场景。",
          "bullets": [
            "紧迫deadline下，在Map中引入独立状态而非新函数——简化客户接入（Java）",
            "构建checkpoint恢复机制——客户可从失败点恢复，无需重跑",
            "解决分布式边缘场景：竞态条件、并发更新、依赖服务故障、消息去重",
            "负责服务oncall——构建CloudWatch仪表盘，编写runbook，实时调试生产问题"
          ]
        }
      ]
    },
    "experience": {
      "title": "工作经历",
      "subtitle": "欢迎向Poimen了解更多",
      "items": [
        {
          "company": "Poimen (Ποιμήν)",
          "role": "架构师 / 智能体工程师",
          "period": "2025年5月 — 至今",
          "description": "Poimen（\"牧羊人\"）— 自学习智能体平台，两大支柱：\n\n🧠 <b>记忆</b>：<b>Rust</b> <b>Graph-RAG</b> 服务。固定窗口分块 → <b>TEI</b> 嵌入 → <b>pgvector</b> + 双向图索引。三层 <b>RRF 融合</b>检索：签名匹配（<b>50ms</b>）、图增强混合搜索、<b>Obsidian</b> 回退。自压缩缓存淘汰过时嵌入，每次写入自动协调图。\n\n⚡ <b>工作流</b>：<b>Go</b> + <b>Temporal</b> 持久化执行引擎。LLM 路由器从自然语言生成 <b>WorkflowSpec</b>，基于<b>活动知识库</b>（9个活动，含超时/重试/依赖元数据）。<b>JSONPath</b> 参数链、catch 恢复、<b>精确一次</b>保证。<b>目标驱动</b>：描述意图 → 平台组装、执行并自愈。"
        },
        {
          "company": "riotpiao.com",
          "role": "DevOps / SRE / 软件开发",
          "period": "2025年5月 — 至今",
          "description": "从零设计并运维<b>生产级裸金属 Kubernetes 平台</b> — 4节点、<b>3控制面</b>、<b>20+服务</b>、<b>99.2%可用性</b>。\n\n🏗️ <b>基础设施</b>：<b>Talos Linux</b> 不可变OS、<b>etcd</b> 分布式共识、<b>Longhorn</b> 块存储、<b>MinIO</b> S3、<b>CloudNativePG</b> + <b>pgvector</b>。解决了200ms网络延迟导致的 etcd 选主失败 — 重新设计物理拓扑至 5ms 以下 RTT。\n\n🔄 <b>GitOps & CI/CD</b>：从纯 <b>Terraform</b> 演进为 <b>Terraform</b>（节点配置）+ <b>ArgoCD</b>（应用交付）。<b>Kustomize</b> overlay、<b>SOPS</b> 加密密钥、<b>Forgejo CI</b> + DinD 运行器。零手动部署。\n\n🔐 <b>安全与身份</b>：<b>Authentik OIDC SSO</b> + <b>RBAC</b>。<b>Cloudflare Tunnel</b> 零信任入口、<b>cert-manager</b> 自动TLS。\n\n📊 <b>可观测性</b>：<b>Prometheus</b> + <b>Grafana</b> + <b>Loki</b> + <b>Tempo</b> — 全栈指标、日志、追踪、告警。\n\n🤖 <b>AI/ML 服务</b>：<b>vLLM</b> GPU推理（<b>Qwen3-32B</b>）、<b>KServe</b> 模型编排、<b>TEI</b> 嵌入、<b>Ollama</b> 轻量模型。"
        },
        {
          "company": "RBC",
          "role": "技术主管",
          "period": "2024年11月 — 2026年5月",
          "description": "领导多云 IaC 基础设施平台工程，服务 <b>12 个团队</b>。\n\n🏗️ <b>状态迁移</b>：将 <b>500+ Terraform</b> 资源状态文件从 S3 迁移至 <b>JFrog Artifactory</b>。plan/apply 拆分为<b>不可变制品管道</b>，限流并行度 — 消除 <b>503 超时</b>、锁竞争，迁移后<b>零状态损坏</b>。\n\n🔍 <b>漂移检测</b>：构建夜间 <b>cron 漂移检测</b> + <b>Slack</b> 告警 — 配置漂移可见性从 <b>3周 → &lt;24小时</b>。\n\n⚡ <b>工作流编排</b>：引入 <b>Temporal</b> 持久化工作流。标准化 <b>IaC 模式</b> — <b>3倍集成速度</b>。\n\n<b>技术栈</b>：<b>Terraform</b>、<b>OpenShift</b>、<b>Docker</b>、<b>Golang</b>、<b>Grafana</b>、<b>Artifactory</b>、<b>Temporal</b>"
        },
        {
          "company": "AWS",
          "role": "高级软件工程师 (Step Functions)",
          "period": "2022 — 2024",
          "description": "端到端负责 <b>AWS Step Functions</b> 的 <b>Distributed-Map</b> — <b>57+ 区域</b>、<b>P99 &lt;100ms</b>。\n\n🚀 <b>功能负责</b>：发布 <b>Redrive Execution</b> — 分布式工作流从失败点重试。设计 <b>JSON 状态输入</b>支持更大负载。在代码审查中发现破坏性<b>条件字段变更</b> — 协调前后端同步部署，防止客户影响。\n\n📊 <b>运维卓越</b>：构建 <b>CloudWatch</b> 仪表盘、编写运维手册、负责<b>值班轮换</b>。保持前后端发布周期<b>向后兼容</b>。\n\n🔧 <b>分布式系统</b>：<b>DynamoDB</b> 分区设计、<b>gRPC</b> 服务网格、<b>灾备</b>规划、<b>多区域</b>复制。\n\n<b>技术栈</b>：<b>Java</b>、<b>AWS</b>、<b>DynamoDB</b>、<b>CloudWatch</b>、<b>gRPC</b>、<b>Step Functions</b>"
        },
        {
          "company": "Titus",
          "role": "软件工程师实习",
          "period": "2019年5月 — 8月",
          "description": "数据分类安全初创公司 — 构建检测与连接器系统。\n\n🔍 <b>异常检测</b>：构建<b>个人数据检测</b>管道，标记机密数据外泄 — <b>97.8% 准确率</b>。\n\n⚡ <b>连接器</b>：容错 <b>Golang</b> 数据连接器 — <b>P99 提升 28%</b>。\n\n🔧 <b>构建系统</b>：<b>CMake</b> + <b>C++</b> 重新集成 <b>SmartRegex</b> 引擎 — <b>部署速度提升 5 倍</b>。\n\n<b>技术栈</b>：<b>Golang</b>、<b>C++</b>、<b>CMake</b>、<b>Docker</b>、<b>Linux</b>"
        },
        {
          "company": "NAV Canada",
          "role": "暑期实习生",
          "period": "2018年5月 — 8月",
          "description": "空管软件 — 航班计划与气象简报的企业级 Web 应用。\n\n✈️ <b>FWGS 气象简报</b>：构建 <b>ReactJS</b> 气象简报界面，供<b>空管人员</b>查看实时航班气象数据。\n\n🗳️ <b>NOTAMJ 投票</b>：<b>Django</b> 投票应用，<b>Agile</b> 工作流中达成迭代目标。\n\n📊 <b>质量</b>：通过 <b>SonarQube</b> 代码覆盖率集成提升企业 <b>CFPS</b> 平台部署稳定性。\n\n<b>技术栈</b>：<b>ReactJS</b>、<b>Django</b>、<b>SonarQube</b>、<b>Agile</b>"
        }
      ]
    },
    "terminal": {
      "title": "Poimen（代理终端）",
      "button": "问Poimen",
      "helpText": "输入 'help' 查看命令"
    },
    "footer": {
      "copyright": "© 2025 梁伟哲。部署于家庭实验室Kubernetes集群（4节点Talos）。",
      "github": "GitHub",
      "email": "邮箱"
    }
  }
}