{ "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": "Homelab: Self-Hosted Cloud", "description": "Production-grade cloud platform rebuilt from scratch on bare-metal Kubernetes.", "longDescription": "4-node Talos cluster (3 control plane + 1 worker) with OIDC SSO, GitOps (ArgoCD), CI/CD, Kafka, PostgreSQL, S3 storage, GPU LLM inference, and Temporal workflows.", "stat": "4 nodes, 20+ services, 99.2% uptime", "highlight": "AWS rebuilt at home—full stack from compute to observability.", "bullets": [ "Kubernetes (Talos Linux) + ArgoCD GitOps + Terraform IaC + Kustomize manifests", "Authentik OIDC SSO + RBAC + SOPS encrypted secrets + cert-manager TLS", "Longhorn block storage + MinIO S3 + CloudNativePG PostgreSQL + pgvector", "Prometheus + Grafana + Loki + Tempo + OpenTelemetry observability stack", "vLLM GPU inference (Qwen3-32B) + Ollama + TEI embeddings + KServe orchestration", "Temporal workflows + Kafka/Redpanda streaming + Forgejo CI/CD + DinD runners", "Go API gateway + Python ML + Next.js frontend + Cloudflare Tunnel zero-trust" ], "deepDive": { "label": "Deep Dive: Homelab Architecture →", "url": "/homelab" } }, { "title": "Poimen Memory System", "description": "Distributed Graph-RAG infrastructure with hierarchical RBAC and wiki-link indexing.", "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": "Poimen: Agent Workflow Orchestration", "description": "Temporal-powered orchestration that transforms natural language into durable, scalable workflow executions.", "longDescription": "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 step in the reconciliation pipeline.", "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": "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": "riotpiao.com", "role": "DevOps / SRE / SDE", "period": "May 2025 — Present", "description": "Architected and operates a production-grade, self-hosted cloud platform on bare-metal Kubernetes—featuring OIDC SSO with RBAC, GitOps-driven infrastructure, CI/CD with container registry, Kafka message queuing, managed PostgreSQL, S3-compatible object storage, GPU-accelerated LLM inference, and workflow orchestration. Essentially AWS rebuilt from scratch at home." }, { "company": "RBC", "role": "Lead Software Engineer", "period": "Nov 2024 — May 2026", "description": "Deployments were manual and slow—teams blocked 2+ hours waiting. Chose Terraform for idempotent drift handling, Temporal for multi-cloud orchestration with built-in retry. Cut deploy time to 20min, consolidated public cloud and on-prem into single platform with 99.2% automation and notification-driven operator fallback." }, { "company": "AWS", "role": "Senior Software Engineer (Step Functions)", "period": "2022 — 2024", "description": "Owned Distributed-Map from design doc to production launch across 57+ regions. Full lifecycle: planning, implementation, oncall, status reporting—we built it, we fixed what we broke." }, { "company": "Titus", "role": "Software Engineer Intern", "period": "May — Aug 2019", "description": "Streamlined Personal Data Detection to detect anomaly exit of classified data—achieved 97.8% accuracy. Built fault-tolerant Golang connector—28% p99 improvement over legacy. Re-integrated SmartRegex with CMake & C++ on Linux/Unix—5x faster deployment." }, { "company": "NAV Canada", "role": "Summer Student", "period": "May — Aug 2018", "description": "Maintained enterprise web app CFPS in Agile development process. Built Django NOTAMJ polls app to meet iteration goals. Improved deploy stability with Sonar code coverage. Created FWGS weather briefing interface with ReactJS for ATC." } ] }, "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": "家庭实验室：自托管云", "description": "在裸机Kubernetes上从零构建的生产级云平台。", "longDescription": "4节点Talos集群（3控制平面+1工作节点），具备OIDC SSO、GitOps (ArgoCD)、CI/CD、Kafka、PostgreSQL、S3存储、GPU LLM推理、Temporal工作流。", "stat": "4节点，20+服务，99.2%可用性", "highlight": "在家重建AWS——从计算到可观测性的完整栈。", "bullets": [ "Kubernetes (Talos Linux) + ArgoCD GitOps + Terraform IaC + Kustomize", "Authentik OIDC SSO + RBAC + SOPS加密密钥 + cert-manager TLS", "Longhorn块存储 + MinIO S3 + CloudNativePG PostgreSQL + pgvector", "Prometheus + Grafana + Loki + Tempo + OpenTelemetry可观测性栈", "vLLM GPU推理 (Qwen3-32B) + Ollama + TEI嵌入 + KServe编排", "Temporal工作流 + Kafka/Redpanda流处理 + Forgejo CI/CD + DinD运行器", "Go API网关 + Python ML + Next.js前端 + Cloudflare Tunnel零信任" ], "deepDive": { "label": "深入了解：家庭实验室架构 →", "url": "/homelab" } }, { "title": "Poimen记忆系统", "description": "具有分层RBAC的分布式图RAG基础设施和维基链接索引。", "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": "Poimen: 智能体工作流编排", "description": "Temporal驱动的编排平台，将自然语言转化为持久、可扩展的工作流执行。", "longDescription": "LLM路由器分析用户意图，从语义记忆中检索相关知识，生成可执行工作流规格——支持大规模智能体部署，任何活动可作为协调管道的步骤。", "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": "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": "riotpiao.com", "role": "DevOps / SRE / 软件开发", "period": "2025年5月 — 至今", "description": "在裸机Kubernetes上架构并运维生产级自托管云平台——具备OIDC SSO + RBAC、GitOps驱动的基础设施、CI/CD容器仓库、Kafka消息队列、托管PostgreSQL、S3兼容对象存储、GPU加速LLM推理、工作流编排。相当于在家从零重建AWS。" }, { "company": "RBC", "role": "技术主管", "period": "2024年11月 — 2026年5月", "description": "部署流程手动且缓慢——团队等待2+小时。选择Terraform处理幂等漂移，Temporal用于多云编排和内置重试。将部署时间缩短至20分钟，整合公有云和本地部署为统一平台，99.2%自动化，通知驱动的运维人员兜底机制。" }, { "company": "AWS", "role": "高级软件工程师 (Step Functions)", "period": "2022 — 2024", "description": "负责Distributed-Map从设计文档到57+区域生产发布的全生命周期。完整流程：规划、实现、oncall、状态汇报——我们构建，我们修复。" }, { "company": "Titus", "role": "软件工程师实习", "period": "2019年5月 — 8月", "description": "优化个人数据检测系统，识别机密数据异常流出——准确率97.8%。构建容错Golang连接器——p99延迟比旧版提升28%。用CMake & C++在Linux/Unix上重新集成SmartRegex——部署速度提升5倍。" }, { "company": "NAV Canada", "role": "暑期实习生", "period": "2018年5月 — 8月", "description": "在敏捷开发流程中维护企业级Web应用CFPS。构建Django NOTAMJ轮询应用达成迭代目标。通过Sonar代码覆盖率检查提升部署稳定性。用ReactJS为ATC创建FWGS天气简报界面。" } ] }, "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" } } }