工作经历Experience
PDF 版：PDF: 中文Chinese · 英文English
2026.06 – 至今Jun 2026 – now
AI 解决方案（AI Solutions & Adoption）AI Solutions & Adoption
Digital Luxury Group 中国区（湍澜）· 上海，总部在日内瓦Digital Luxury Group China · Shanghai, HQ in Geneva
全员 AI 转型｜从选型到全员培训Company-wide AI adoption｜from tool selection to training
独立负责：整体策划、选型评估、落地推进、课程设计与全程授课Sole owner: planning, tool evaluation, rollout, course design and delivery
- 背景：管理层提出全员 AI 转型。此前公司以单一 SaaS 工具推动全员 AI 化，推进近一年未取得突破；员工使用 AI 仍以对话框问答为主，对实际工作效率的提升有限。Context: Leadership set a goal of company-wide AI adoption. An earlier attempt to drive it through a single SaaS tool had stalled for nearly a year, and staff still used AI mainly as a chat window, with little effect on day-to-day productivity.
- 需求调研：访谈各团队的 AI 使用现状与工作流痛点，确认推广受阻的根源在于认知缺口：员工并不了解 Agent 能承担哪些工作。Discovery: interviewed each team on current AI use and workflow pain points, and traced the stalled rollout to a gap in understanding: people did not know what work an agent could take on.
- 推广策略：放弃自上而下推行单一工具，改为先在小范围试点、建立可复制的使用范例，再分批推广至全员。Rollout strategy: replaced the top-down push of a single tool with a small pilot that produced repeatable examples, followed by a phased rollout to all staff.
- 选型评估：横向对比腾讯 WorkBuddy 及火山引擎、阿里云等 MaaS 平台，以数据安全为首要标准确定 Claude Code + DeepSeek 方案；独立撰写选型报告并获管理层批准，为全员配置独立 API Key。Tool evaluation: benchmarked Tencent WorkBuddy against MaaS platforms including Volcano Engine and Alibaba Cloud, with data security as the primary criterion, and selected Claude Code + DeepSeek; wrote the evaluation report, secured leadership approval, and issued every employee an individual API key.
- 课程设计与授课：围绕业务流程独立设计课程并全程授课；依据试点反馈多轮迭代，将核心概念拆解为循序渐进的模块，并以完成度高的实际案例开场，提升学员投入度。Curriculum and teaching: designed a course around real business workflows and taught every session; iterated over several rounds of pilot feedback, breaking core concepts into progressive modules and opening with polished real-world demos to hold attention.
- 成果：全员课覆盖 31 人、分 12 组授课；Agent 已进入同事的日常工作流程，多位同事自主开发 Skill，例如文案同事搭建的竞品文案工具，可自动汇总竞品过往文案，并参照其语气改写新稿。Result: The company-wide course reaches 31 people across 12 cohorts; agents are now part of daily workflows, and several colleagues have built their own skills, such as a copywriter's tool that collects competitors' past copy and adapts its tone for her next draft.
客户月报自动化｜接手停滞项目，两周完成开发Client report automation｜revived a stalled project, built in two weeks
独立负责：项目接手与推进、数据盘点、方案设计、工具开发、跨团队协作与培训推广Sole owner: taking over and driving the project, data audit, solution design, development, cross-team coordination, training and rollout
- 背景：客户执行团队需按月为每家客户交付社媒月报，单份从取数、制作到返修平均耗时约 35 小时。该项目此前推进近一年未能落地，后由我接手。Context: Account teams deliver a monthly social media report for every client, each taking about 35 hours from data pull to revisions. The project had failed to ship for nearly a year before I took it over.
- 数据盘点：历时一至两个月，借助 AI 梳理客户执行日常所需的数据资产，明确需定期更新的数据项，协同数据团队完成更新，并统一接入 Brand Knowledge MCP。Data audit: over one to two months, used AI to map the data assets account teams rely on and identify what needed regular refreshes, then worked with the data team to update them and consolidate access through a single Brand Knowledge MCP.
- 工具开发：基于 Claude Code 独立开发，两周完成从立项到可用；采用「通用引擎 + 客户配置」架构适配各家定制版式，产出后自动质检。Development: built the tool solo with Claude Code, from kickoff to working version in two weeks; an engine-plus-client-config architecture handles each custom layout, with automated QC on every output.
- 上线推广：与全员 AI 转型并行推进，9 月末正式上线；完成客户执行团队全员培训并持续指导上手，交由业务团队在日常工作中自主使用。Launch and rollout: delivered in parallel with the company-wide AI programme and launched at the end of September; trained the full account team, coached them through adoption, and handed day-to-day use over to the business.
- 成果：一句指令即可生成 pptx + pdf 报告，单份月报耗时由约 35 小时缩短至十几分钟；已覆盖中国区十余家客户，现有客户的月报与季报均可通过该工具完成；三套数据库整合为全公司统一的数据入口。Result: A single instruction produces a pptx + pdf report, cutting each one from about 35 hours to 10–20 minutes; the tool covers more than ten clients in China and every current client's monthly and quarterly reports; the three databases now sit behind one company-wide entry point.
2025.03 – 2026.05Mar 2025 – May 2026
游戏助理制作人 → AI 工程负责人 → AI 技术架构顾问（2026.03 起，远程）Associate Producer → AI Engineering Lead → AI Tech Architecture Consultant (from Mar 2026, remote)
Rejet Co., Ltd. · 上海（日本乙女向游戏公司上海工作室）Rejet Co., Ltd. · Shanghai studio of a Japanese otome game company
游戏制作里的 AI｜剧本审查 · CG 构图 · 配乐参考AI in game production｜script review · CG composition · music references
独立负责：自学与技术选型、需求梳理与 PRD、工具开发、资源申请与推广Sole owner: self-teaching and tool selection, requirements and PRDs, development, resourcing and rollout
- 背景：乙女向游戏的剧本、CG 与配乐体量都很大：百万字级剧本的校对与风险审查由三至五名编剧与我按章节通读，一轮需两三周；每张 CG 须先出构图草稿，审核通过后才能派发绘制。Context: Otome games run on very large volumes of script, CG and music: proofreading and risk review of a million-character script took three to five writers and me two to three weeks per pass, chapter by chapter, and every CG needed an approved composition draft before it could be assigned.
- 从零自学：在项目管理工作之外自学 Agent，从对话式 AI 转向 Agent 工作流，独立完成需求梳理、PRD 撰写与工具开发。Self-taught from zero: learned agents alongside my project-management work, moving from chat-based AI to agent workflows, and handled requirements, PRDs and development myself.
- 剧本：搭建全自动校对流程，由 Antigravity 拆分剧本并送入自建校对工具，识别人工易遗漏的风险项，按场景编号输出问题清单，修改决定权留给编剧。Scripts: built a fully automated proofreading pipeline in which Antigravity splits each script and feeds it into my own tool, which flags risks reviewers tend to miss and lists them by scene number, leaving every edit to the writers.
- CG 与配乐：以人设图、定稿图与服装图批量生成构图参考，由画师重新绘制，最终画面保持手绘；配乐评估开源模型后改用 MIDI 程序化生成参考。CG and music: batch-generated composition references from character sheets, final designs and costume art for artists to redraw, so final art stays hand-drawn; for music, evaluated open-source models and switched to programmatic MIDI references.
- 争取资源：撰写资源申请，测算出图成本并提出用量控制方案，推动公司提供模型账号与项目文件权限。Securing resources: wrote the resource requests, with per-image cost estimates and usage controls, and obtained model accounts and access to project files.
- 成果：剧本审查周期由两三周缩短至一两晚；CG 前期由检索素材、手绘草稿转为批量生成构图参考；配乐参考为前期调研提供调性依据。基于上述成果，由项目管理岗调任 AI 工程负责人。Result: Script review went from two to three weeks to one or two nights; CG pre-production moved from reference hunting and hand sketches to batch-generated composition references; the music references set the tonal direction for pre-production. On the strength of this work I moved from project management to AI engineering lead.
2023.11 – 2024.04Nov 2023 – Apr 2024
产品设计师（UI/UX）Product Designer (UI/UX)
HCM Capital · 上海HCM Capital · Shanghai
- 端到端设计执行：需求分析 → Figma 高保真 UI → 设计系统搭建End-to-end design: requirements → high-fidelity Figma UI → design system
- 与产品经理和工程师协作，输出设计规范文档和部分 PRDDesign specs and PRD sections with PMs and engineers
2022.02 – 2023.03Feb 2022 – Mar 2023
项目协调员 & 设计主管Project Coordinator & Design Lead
SKY LILAH / VVAF · 加拿大温哥华SKY LILAH / VVAF · Vancouver, Canada
- 参与品牌焕新与官网重建，协助从策略到视觉执行的落地Brand refresh and website rebuild, from strategy to visual execution
- 统筹 Art Vancouver 2022 策展协助与现场执行，协调多方资源Coordinated Art Vancouver 2022: curation support and on-site execution
核心技能Core skills
- AI 落地AI adoption
- 需求调研 · 工具选型与数据安全评估 · 推广策略 · 课程设计与授课Discovery · tool selection and data-security review · rollout strategy · course design and teaching
- AI 工程AI engineering
- Claude Code · Agent / Skill / MCP · 基于模型 API 的工具开发 · 自动化流程搭建 · SQL / BigQueryClaude Code · agents, skills and MCP · tools built on model APIs · automated workflows · SQL / BigQuery
- 项目推进Delivery
- 接手并推进停滞项目 · 跨团队协作 · 资源申请与成本测算 · PRD 撰写Reviving stalled projects · cross-team coordination · resourcing and cost estimates · PRDs
- 设计Design
- 交互设计 · UI/UX · Figma · 设计系统Interaction design · UI/UX · Figma · design systems
- 语言Languages
- 中文（母语）· 英语（流利，8 年加拿大经历）Mandarin (native) · English (fluent, 8 yrs in Canada)
教育背景Education
- 2015 – 2020
- Simon Fraser University · 互动艺术与技术学士（SIAT）Simon Fraser University · B.A., Interactive Arts & Technology (SIAT)
- 2020 – 2021
- Vancouver Film School · 视觉媒体声音设计Vancouver Film School · Sound Design for Visual Media
联系我Get in touch