John Wang

Full-Stack Engineer | Industrial Digitization, Cloud-Native Platforms, and AI Agent Delivery

GitHub: github.com/myysophia Email: john.mr.wx@gmail.com Target Roles: Full-Stack AI Application Development / Platform Engineering Education: Bachelor's Degree Experience: 9 years

Profile

Full-stack engineer with experience spanning business system delivery, platform engineering, and AI Agent application development, covering industrial digitization, cloud-native container platforms, and intelligent applications.

Repeatedly owned zero-to-one system delivery across core business domains, combining frontline business understanding with architecture design, technical execution, and cross-functional delivery.

Recently focused on AI Agent applications, connecting requirement breakdown, tool orchestration, backend services, frontend interaction, and observability into deployable and maintainable product workflows.

Work Experience

AI Agent Application Development | AI Business Team

2023/12 - 2025/08

Built AI Agent applications from solution design and tool orchestration to full-stack integration, turning model capabilities into closed-loop business workflows.

  • Led practical implementation of conversational Agents, tool calling, and RAG workflows across business scenarios, covering requirement analysis, execution-chain design, API implementation, and user interaction.
  • Built an engineering foundation for Agent applications, including task execution, streaming responses, exception handling, audit logs, and observability.
  • Coordinated frontend, backend, and runtime environments to move intelligent capabilities from demos toward deployable, traceable, and continuously iterative systems.
  • Balanced stability, maintainability, and explainability across complex task flows to improve delivery quality and operational control.

Container Platform Development | Platform Engineering Team

2022/10 - 2023/08

Participated in container platform development and cloud-native capability building, supporting application containerization, platformization, and standardized delivery.

  • Contributed to container platform capabilities that supported migration from traditional deployment models to container-based delivery.
  • Worked with Kubernetes and Docker to support service deployment, configuration management, and runtime standards.
  • Built practical experience in cloud-native architecture, service operations, and platform engineering, forming a foundation for later AI application delivery.

QMS / RTM / Big Data Analytics Platform | State-Owned Semiconductor-Related Enterprise

2017/07 - 2022/08

Worked deeply in semiconductor-related manufacturing scenarios, building quality management, production yield monitoring, and analytics platforms from zero to one to support production improvement and management decisions.

  • Led the zero-to-one delivery of QMS, from requirement analysis and process abstraction to system implementation, helping quality management move toward process-driven and data-driven operations.
  • Led the zero-to-one delivery of RTM for production yield monitoring, building visual and traceable loops around production anomalies, yield fluctuation, and key manufacturing indicators.
  • Supported production yield ramp-up through system capabilities and data analysis, helping manufacturing teams locate issues, improve processes, and coordinate decisions.
  • Built a big data analytics platform for manufacturing data, consolidating quality data, production data, and analysis capabilities for broader cross-team usage.
  • Collaborated with production, quality, process, and engineering stakeholders over multiple years, translating complex manufacturing needs into maintainable systems and iterative delivery plans.

Role Fit

Industrial Digitization

Experience building core manufacturing systems from zero to one and turning complex workflows into evolvable system capabilities.

Platform Engineering

Hands-on container platform and Kubernetes delivery experience, with a practical understanding of engineering efficiency and runtime stability.

AI Agent Engineering

Practical experience with conversational Agents, tool calling, and RAG, with focus on moving prototypes into production-ready applications.

Full-Stack Delivery

Able to deliver across frontend, backend, and deployment layers while coordinating implementation across business and technical teams.

Tech Stack

  • Frontend: React, Next.js, TypeScript, SSE streaming interactions
  • Backend: Go, Python, REST APIs, task orchestration, authentication, rate limiting, error handling
  • AI Applications: RAG, prompt engineering, tool calling, Agent execution flows
  • Data and Analytics: PostgreSQL, Redis, time-series databases, quality data governance, business analytics platforms
  • Cloud-Native and Platform: Docker, Kubernetes, containerized delivery, AWS EKS/ECR, CloudWatch
  • Observability: Prometheus, Grafana, OpenTelemetry, distributed tracing

Selected Projects (AI Agent)

OpsAgent | Kubernetes Intelligent Operations Agent (Go + Kubernetes + RAG)

  • Designed and implemented a conversational Agent for Kubernetes troubleshooting, forming a closed loop from problem understanding to tool execution and result explanation.
  • Implemented cluster resource analysis with client-go, covering Pods, Deployments, Nodes, and Events.
  • Built Docker images and Kubernetes service deployment to run the intelligent operations capability as a service.
  • Integrated CloudWatch and Prometheus to improve execution observability, issue tracking, and post-incident review.

Keywords: Go, Kubernetes, RAG, AI application integration, engineering delivery

cli-agent | AI Tool Execution Gateway (Go + HTTP API + SSE)

  • Wrapped multiple CLI and tool capabilities into HTTP APIs, creating a reusable execution layer for Agent applications.
  • Implemented SSE streaming output for long-running tasks, improving process visibility and interaction quality.
  • Added timeout control, error handling, and audit logs to provide a more reliable runtime foundation.
  • Supported the end-to-end flow from frontend conversation UI to backend task execution.

Keywords: Go, backend APIs, streaming interaction, tool orchestration, full-stack integration

aiagent-ui | Web Console for Operations Assistant (Next.js + TypeScript)

  • Built core pages including conversation lists, task status, and execution result views for intelligent operations scenarios.
  • Integrated with backend Agent services to complete the flow from user request to backend execution and result delivery.
  • Supported SSE incremental rendering to improve transparency and usability during AI reasoning and task execution.

Repo: github.com/myysophia/k8s-aiagent-ui

Keywords: React/Next.js, frontend engineering, full-stack delivery, AI application UI

王九日

全栈工程师|工业数字化、云原生平台与 AI Agent 应用落地

GitHub: github.com/myysophia Email:john.mr.wx@gmail.com 求职方向:全栈 AI 应用开发 / 平台工程 学历:本科 工作经验:9年

个人简介

具备从业务系统建设到平台研发,再到 AI Agent 工程化落地的复合型全栈背景,经历覆盖制造业数字化、云原生容器平台与智能应用研发三个阶段。

职业生涯中多次承担从 0 到 1 搭建核心系统的职责,既能深入理解一线业务场景,也能完成系统架构设计、技术方案落地与跨团队协同推进。

近年聚焦 AI Agent 应用开发,擅长将需求拆解、工具编排、服务实现、前端交互与可观测性建设串联成完整交付链路,推动能力从原型走向可上线、可维护的工程化应用。

工作履历

AI Agent 应用开发|某 AI 业务团队

2023/12 - 2025/08

围绕智能应用落地,负责 AI Agent 产品从方案设计、工具链编排到前后端联动交付的完整研发工作,推动模型能力向业务场景闭环转化。

  • 主导对话式 Agent、工具调用、RAG 等能力在具体业务中的落地,串联需求分析、执行链路设计、接口实现与交互体验建设。
  • 搭建面向实际应用的 Agent 工程化框架,沉淀任务执行、流式回传、异常处理、日志审计与可观测性等关键基础能力。
  • 协同前后端与运行环境,推动智能能力从 Demo 形态演进为可部署、可追踪、可持续迭代的应用系统。
  • 在应用开发过程中兼顾稳定性、可维护性与可解释性,提升复杂任务链路的可控性与交付质量。

容器平台开发|某平台研发团队

2022/10 - 2023/08

参与容器平台研发与云原生能力建设,面向研发交付与服务运行场景,推进应用容器化、平台化与标准化落地。

  • 参与容器平台相关能力开发,支撑业务应用从传统部署方式向容器化交付方式迁移。
  • 围绕 Kubernetes、Docker 等技术栈推进服务化部署、配置管理与运行规范建设,提升研发与交付协同效率。
  • 在平台研发过程中积累云原生架构、服务治理与运行维护经验,为后续 AI 应用工程化提供平台基础。

QMS / RTM / 大数据分析平台建设|某泛半导体行业央企

2017/07 - 2022/08

深耕泛半导体制造场景,围绕质量管理、产线良率监控与数据分析平台建设,持续推动关键业务系统从 0 到 1 落地,并服务于生产改善与管理决策。

  • 主导 QMS(品质管理系统)从需求梳理、流程抽象到系统建设落地,推动质量管理由线下经验驱动向系统化、流程化与数据化升级。
  • 主导 RTM(产线良率监控)系统从 0 到 1 建设,围绕产线异常、良率波动与关键指标监控形成可视化、可追踪的业务闭环。
  • 参与并推动产线良率爬升相关工作,通过系统建设与数据分析支撑制造现场问题定位、工艺改善与协同决策。
  • 搭建面向制造数据的大数据分析平台,沉淀质量数据、生产数据与分析能力,提升跨部门对数据的统一理解与使用效率。
  • 长期与生产、品质、工艺等多角色协作,在复杂业务语境中完成需求抽象、系统设计与持续迭代,具备较强的业务理解与落地推进能力。

岗位匹配亮点

工业数字化系统建设

有制造业核心业务系统从 0 到 1 建设经验,能够把复杂流程沉淀为可持续演进的系统能力。

平台工程与云原生

具备容器平台研发与 Kubernetes 服务化交付经验,理解平台能力对研发效率与稳定运行的价值。

AI Agent 工程化

有对话式 Agent、工具调用、RAG 场景的实际开发经验,关注从原型到可上线应用的工程闭环。

全栈交付与协同推进

可独立完成前端、后端与部署联调,也能在跨团队场景中推进方案落地与系统持续演进。

技术栈

  • 前端:React、Next.js、TypeScript、SSE 流式交互
  • 后端:Go、Python、REST API、任务编排、鉴权/限流/错误处理
  • AI 应用:RAG、Prompt 工程、Tool Calling、Agent 执行链路
  • 数据与分析:PostgreSQL、Redis、时序数据库、质量数据治理、业务分析平台建设
  • 云原生与平台:Docker、Kubernetes、容器化交付、AWS(EKS/ECR)、CloudWatch
  • 可观测性:Prometheus、Grafana、OpenTelemetry、调用链追踪

代表项目(AI Agent 方向)

OpsAgent|Kubernetes 智能运维 Agent(Go + Kubernetes + RAG)

  • 设计并实现面向 K8s 故障排查的对话式 Agent,形成“问题理解 → 工具执行 → 结果解释”的闭环链路。
  • 基于 client-go 实现集群资源分析能力,覆盖 Pod、Deployment、Node、Events 等核心对象。
  • 完成 Docker 镜像构建与 K8s 服务化部署,支撑智能运维能力以服务形式运行与迭代。
  • 接入 CloudWatch/Prometheus,增强问题追踪、执行观测与排障复盘能力。

匹配关键词:Go、Kubernetes、RAG、AI 应用集成、工程化交付

cli-agent|AI 工具执行网关(Go + HTTP API + SSE)

  • 将多类 CLI/工具能力统一封装为 HTTP API,沉淀 Agent 应用可复用的标准执行层。
  • 实现 SSE 流式输出,支持长任务实时回传,提升复杂执行过程的可视化与可理解性。
  • 补齐超时控制、错误处理、审计日志等基础能力,为上层智能应用提供更稳健的运行底座。
  • 支撑“前端会话界面 + 后端任务执行”的端到端链路,降低工具接入与编排复杂度。

匹配关键词:Go、后端 API、流式交互、工具编排、全栈联调

aiagent-ui|运维助手 Web 控制台(Next.js + TypeScript)

  • 负责会话列表、任务状态、执行结果展示等核心页面开发,构建面向智能运维场景的交互入口。
  • 与后端 Agent 服务联调,打通从前端发起、后端执行到结果回传的完整用户路径。
  • 支持 SSE 增量渲染,提升 AI 推理与任务执行过程的透明度和可用性。

Repo:github.com/myysophia/k8s-aiagent-ui

匹配关键词:React/Next.js、前端工程、全栈交付、AI 应用界面