模拟面试提问 Mock Interview

AI 买宇翔 · 数字分身 Yuxiang · Digital Twin
买宇翔

你好,我是买宇翔(英文名 Miles)。有什么问题尽管问我,我会用第一人称回答。

Hi, I'm Yuxiang Mai (Miles). Ask me anything—I'll answer in first person.

金融 AI 产品 FDE Finance AI PM · FDE

金融 AI 产品经理 · CFA 持证人 · 10 年金融 + AI 解决方案落地 Financial AI PM · CFA Charterholder · 10 Years in Finance + AI Solutions

工作经历 Work Experience

Business Analysis Officer Business Analysis Officer

2021.11 — 至今

美国道富(浙江)有限公司 State Street (Zhejiang) Co., Ltd.

AI智能对账自动化项目负责人 | 2025 - 至今 AI Reconciliation Automation Project Lead | 2025 – Present

  • 从日常BA工作中发现运营团队手工对账环节占工时超40%的核心痛点,联合运营部门做根因分析,作为AI解决方案主导自动化立项
  • 主导AI对账Agent从需求到交付:撰写PRD,提出可解释AI三层处理架构(规则引擎+AI Agent+人工兜底),确保合规可控;对接Bloomberg等第三方数据源建立 tool call获取实时估值与持仓数据,规划三阶段灰度发布策略
  • 协同运营、合规与技术团队推动上线,上线后人工对账工时缩短近40%
  • Identified from daily BA work that manual reconciliation consumed over 40% of the operations team's hours; ran root-cause analysis with the operations department and led the automation initiative as an AI solution.
  • Drove the AI reconciliation Agent from requirements to delivery: authored the PRD, proposed an explainable-AI three-tier architecture (rules engine + AI Agent + human fallback) ensuring compliance and controllability; integrated Bloomberg and other third-party data sources via tool calls for real-time valuation and position data; planned a three-phase canary release strategy.
  • Coordinated operations, compliance, and engineering teams to drive rollout; reduced manual reconciliation hours by nearly 40% post-launch.

推动团队AI转型与AI工具日常应用 | 2024 - 至今 Team AI Transformation & Daily AI Tool Adoption | 2024 – Present

  • AI Workflow工作流梳理:推动团队采用自然语言描述→自动生成AS-IS/TO-BE流程图草稿
  • AI测试用例生成:推动测试团队基于PRD验收标准,用AI批量生成边界值与异常场景测试用例
  • AI组织转型:组织Copilot使用培训,带动团队从工具试用向常态化AI工作流转型
  • AI Workflow streamlining: drove the team to adopt natural-language-to-flowchart generation, replacing manual Visio drawing — BAs produce AS-IS/TO-BE flowchart drafts by describing business steps.
  • AI test-case generation: guided the QA team to batch-generate boundary and edge-case test cases from PRD acceptance criteria using AI.
  • AI organizational transformation: organized Copilot training, shifting the team from tool trial to normalized AI-workflow adoption.

资管数据平台迭代升级 | 2022 - 至今 Asset Management Data Platform — Iteration & Upgrade | 2022 – Present

  • 推动CRIMS前台交易系统与SSCD数据报告系统融合,参与多次版本迭代,解决前台交易与后台报告数据割裂问题
  • 制定UAT测试策略,编写测试用例,拦截10+个高危缺陷;对接美欧客户需求,通过Jira管理Backlog与Sprint,推动产品交付
  • Drove the convergence of the CRIMS front-office trading system with the SSCD data reporting system across multiple version iterations, resolving the disconnect between front-office trading and back-office reporting data.
  • Defined the UAT test strategy and authored test cases, intercepting 10+ high-severity defects; gathered requirements from US/EU clients, managed Backlog and Sprint via Jira, and drove product delivery.

客户定制化产品敏捷交付 | 2023-2025 Client Customized Product Agile Delivery | 2023–2025

  • 主导Settled Cash Reconciliation Report与Daily Detailed NAV Compare Report等客户定制产品从需求到上线,自动化报告生成节约运营时间约70%
  • Led client-customized products such as the Settled Cash Reconciliation Report and Daily Detailed NAV Compare Report from requirements to launch; automated report generation cut operations time by ~70%.

高级基金会计 Senior Fund Accountant

2021.06 — 2021.08

CITCO(加拿大)有限公司 CITCO (Canada) Inc.

  • 管理多只私募股权基金的会计核算与资产估值,审查财务数据并编制NAV报告,协调资金催缴及收益分配;因疫情及家庭原因决定回国发展
  • Managed accounting and asset valuation for multiple private-equity funds, reviewed financial data and prepared NAV reports, and coordinated capital calls and distributions; returned to China due to pandemic and family reasons.

Operations Associate Operations Associate

2019.7 — 2021.1

SS&C Technologies(加拿大) SS&C Technologies (Canada)

  • 与券商及基金经理合作核算交易差异、控制交易风险,使用彭博终端验证场内场外衍生品定价;开发自动化工具将数据导入时间从2小时缩短至15分钟
  • Partnered with brokers and fund managers to resolve trade breaks and control trading risk; validated exchange-traded and OTC derivatives pricing using the Bloomberg Terminal; developed automation tooling that cut data-import time from 2 hours to 15 minutes.

运营分析师 Operations Analyst

2017.5 — 2019.5

CITCO (Canada) Inc CITCO (Canada) Inc

  • 管理多资产类别基金交易运营与每日现金对账,开发期货佣金对账等自动化工具覆盖数据提取到报表生成,将手工处理时间从8小时缩短至1小时,累计节省0.5个FTE
  • Managed multi-asset fund trade operations and daily cash reconciliation; built automation tooling (e.g., futures commission reconciliation) covering data extraction to report generation, cutting manual processing time from 8 hours to 1 hour and saving 0.5 FTE cumulatively.

合伙人-辅导老师(自雇) Partner / Tutor (Self-employed)

2014.9 — 2017.4 全职,2017.5 — 2019.6 兼职

博洋教育 Boyang Education

  • 主讲本科及硕士商科金融课程(公司金融、投资组合管理、衍生品等),编写备课方案,培训新辅导老师;组建并运营本地CFA培训项目
  • Taught undergraduate and graduate finance courses, authored lesson plans, trained new tutors, and built and ran a local CFA training program.

个人项目 Personal Projects

Lumina Lumina

通用 AI Working Agent 应用 General-Purpose AI Working Agent

  • 对标 Claude Code 等通用 Agent,采用 Agent Loop 和子派生 Agent Harness 架构,支持 Skill 扩展
  • 特色功能:对话地图分叉机制支持同一任务多决策路径调试对比
  • Benchmarks against Claude Code and other general-purpose Agents; built on Agent Loop and sub-derived Agent Harness architecture; supports Skill extensions.
  • Signature feature: conversation-map branching mechanism enables debugging and comparing multiple decision paths for the same task.

StockResearch StockResearch

Multi-Agent AI 投研终端(GitHub 100+ ⭐) Multi-Agent AI Research Terminal (GitHub 100+ ⭐)

  • 面向智能投研与智能投顾场景:多 Agent 并行架构(基本面/技术面/情绪面/宏观面)独立分析后交叉辩论,裁判 Agent 输出结论,内置金融知识库驱动跨资产研究推理
  • 双模式设计(引导式/全功能),适配从投顾新手到专业研究员的不同经验用户
  • Targeting AI investment research and advisory scenarios: a multi-Agent parallel architecture where fundamental, technical, sentiment, and macro Agents analyze independently, then cross-debate — with a judge Agent synthesizing the final output. A built-in financial knowledge base powers cross-asset reasoning.
  • Dual-mode design (guided / full-feature) adapts to users from advisory novices to professional researchers.

NoteAI NoteAI

本地 RAG 知识图谱应用 Local RAG Knowledge-Graph App

  • 从知识碎片化痛点出发,采用向量数据库+结构化知识库双检索,实现知识消化→知识编译→语义问答闭环
  • 特色功能:Top-K 等多项RAG参数,支持根据用户反馈数据自动进行参数调整
  • Starting from the pain point of fragmented knowledge, adopted vector database + structured knowledge base dual retrieval, enabling a closed loop of knowledge ingestion → knowledge compilation → semantic Q&A.
  • Signature feature: Top-K and other RAG parameters with automatic tuning based on user feedback data.

教育背景 Education

金融学 · 硕士 MSc Finance

2013 — 2014

圣玛丽大学 Saint Mary's University

经济学 · 本科 BSc Economics

2008 — 2012

河南工业大学 Henan University of Technology