Available from 04/2026 — Seeking AI Product / Fintech / LLM Roles

Hello, I'm

Longyu Xu

AI Product Manager • Fintech • LLM Applications

View ResumeView ProjectsContact Me
longyu.xu@edhec.com
Scroll
Flagship Project · IBM AML NeurIPS 2023 · PBOC · claude-sonnet-4-6

AML Sentinel

China AML Intelligence Platform

Production-grade AML compliance workbench built on real IBM AML NeurIPS 2023 fraud data, PBOC regulatory rules engine, and an AI Agent that auto-drafts Suspicious Transaction Reports in CAMLMAC format.

84
Real Alerts
IBM AML Dataset
71
AML Cases
Network Visualization
55
Regulation Chunks
4 Legal Documents
6
Agent Steps
claude-sonnet-4-6
longyuxu.xyz/en/aml-sentinel
AML Sentinel
China AML Intelligence Platform
84
Total Alerts
+3 today
23
Critical
Require action
71
Active Cases
8 pending
¥1.2B
Vol. Flagged
Last 30 days
Alert Queue
Case Overview
Network Analysis
Regulatory RAG
STR Draft
Alert IDAmountTypeRisk ScoreStatus
TXN-0001¥68,000Cash
82
CRITICAL
TXN-0002¥3,200,000Transfer
74
HIGH
TXN-0003¥49,500Cash
61
HIGH
TXN-0005¥850,000Remittance
68
HIGH
TXN-0012¥2,450,000Transfer
91
CRITICAL
500 alerts
Risk Scoring Engine

PBOC threshold rules + real fraud labels from IBM AML NeurIPS 2023

436 cases
Network Graph

ECharts force-layout · Fan-out, fan-in & cycle pattern detection

55 chunks
Regulatory RAG

4 real AML docs · BM25 retrieval · article-level citations

claude-sonnet-4-6
AI Agent STR Draft

6-step agent loop · CAMLMAC-format report auto-generation

Companion Project #11 · Product Suite with AML Sentinel

ComplianceIQ

Compliance Research Workbench

AML Sentinel handles "finding risks" (transaction monitoring, case investigation, STR drafting). ComplianceIQ handles "finding rules" (regulation search, case comparison, AI-structured analysis). Both share the same regulatory data layer but serve different workflow stages.

What It Solves

Regulation Search Efficiency

Compliance officers traditionally search through multiple PDFs page by page. CJK-aware BM25 search + source filtering reduces regulation lookup from minutes to seconds.

55 chunks · 4 sources · sub-second retrieval

Evidence Layering & Citability

Every AI answer enforces a 5-section structure, strictly separating legal provisions from reference materials — preventing KPMG analysis or FATF reports from being misrepresented as binding regulatory basis.

5-section enforced · Legal vs. Reference layered

Case Comparison & Risk Assessment

25 enforcement cases with control failure analysis, bidirectionally linked to regulations via linkedRegulationIds — helping analysts connect regulatory obligations to actual penalty consequences.

25 cases · bidirectional nav · control failure analysis

Tech Stack & Architecture

Frontend
Next.js 14React 18TypeScriptTailwind CSS
Backend / API
Next.js API RoutesServer-Sent Events (SSE)Anthropic SDK
AI / Retrieval
claude-sonnet-4-6BM25 (CJK bigram)RAGStreaming
Data Layer
AML Law 2024PBOC RulesKPMG AnalysisFATF China 2019
Deployment
VercelEdge Functionsi18n (ZH/EN)
Key Design Decisions
  • Q&A request body excludes case data — server recomputes to prevent client-side evidence tampering
  • Validation failures return 400 JSON (no SSE opened), consistent with existing AML routes
  • isLegalSource() classifies by source semantics, not hardcoded ID ranges
  • pinnedChunks cleared on submit, enforcing single-turn research boundary
PythonSQLLangChainLangGraphPower BIRAGNext.jsEChartsPandasVaR / CVaRFinancial RiskTypeScriptPythonSQLLangChainLangGraphPower BIRAGNext.jsEChartsPandasVaR / CVaRFinancial RiskTypeScript
Prompt EngineeringMachine LearningFinancial AnalysisA/B TestingRegulatory ComplianceAudit AutomationD3.jsRisk ModelingVector DBPBOC / SAFECompliance ReviewData PipelinePrompt EngineeringMachine LearningFinancial AnalysisA/B TestingRegulatory ComplianceAudit AutomationD3.jsRisk ModelingVector DBPBOC / SAFECompliance ReviewData Pipeline
01
About Me

International Finance & Management at EDHEC Business School (GPA 15.66/20, Top 15%), BSc Finance from Shanghai Jiao Tong University (Minor: Information Management). Hands-on experience in risk control, compliance, and data analytics across Paris and Shanghai. Currently focused on AI + Compliance: independently designed and deployed AML Sentinel (AML investigation workbench) and ComplianceIQ (compliance research workbench) as production-grade portfolio demos covering transaction monitoring, regulatory retrieval, enforcement case analysis, and AI-structured Q&A.

Open to opportunities
0+
Internships
0
Degrees
0
Projects
0
Languages
02
What I Do

Cross-domain expertise driving data insights and AI delivery

Financial Risk Analytics

Bridging quantitative models with regulatory frameworks to build risk exposure monitoring, compliance review, and report automation for banking and FinTech.

Risk ModelingRegulatory ComplianceVaR / CVaRPBOC/SAFE

AI Tools & Automation

Exploring RAG, LangChain, and LangGraph tools applied to financial compliance, audit automation, and document analysis.

RAG PipelinesLangChainCompliance AutomationDoc Analysis

Data Analytics & Visualization

End-to-end data pipelines and interactive dashboards using Python, SQL, Power BI, and ECharts, turning raw data into actionable insights.

Python / SQLPower BIECharts / D3A/B Testing
03
Featured Projects

Data-driven projects & analytics tools

Risk AnalyticsAI AgentRAG
Live DemoFeaturedAI Compliance Suite

AML Sentinel: China AML Investigation Workbench

A bank-style AML compliance workbench combining real Chinese financial fraud data (DGraph-Fin by Finvolution), PBOC regulatory RAG, and an AI Agent that auto-drafts Suspicious Transaction Reports — designed around the full analyst investigation workflow.

10 min readView Project
Risk AnalyticsRAGLLM
Live DemoFeaturedAI Compliance Suite

ComplianceIQ: Compliance Research Workbench

A knowledge-driven compliance research workbench that organizes regulatory provisions, enforcement cases, and AI-powered structured explanations into a single searchable, citable, and cross-referenced research workflow for banking compliance professionals.

8 min readView Project
Risk AnalyticsData AnalyticsData Visualization
Live DemoFeatured

Payment Risk Policy & Monitoring Assistant

An interactive compliance workflow tool integrating regulatory requirements, risk-control mapping, scenario scoring, and real-time alert monitoring — built as a B2B internal risk ops prototype.

8 min readView Project
RAGLLMPython
Live DemoFeatured

Financial Document RAG Q&A System

A RAG (Retrieval-Augmented Generation) Q&A system built for Chinese financial regulatory documents (PBOC / SAFE regulations), enabling natural-language compliance queries with precise answers and source citations.

9 min readView Project
AI AgentLLMPython
Live DemoFeatured

Multi-Agent Financial Research Assistant

An LLM-orchestrated multi-agent system that automates financial research pipelines: Data Collection Agent → Quantitative Analysis Agent → Report Generation Agent, with tool use and context memory — compressing research cycles from days to minutes.

10 min readView Project
Product OperationsUser GrowthData Analytics
Live DemoFeatured

User Growth Analytics Platform

An interactive product operations analytics platform featuring AARRR funnel analysis, cohort retention heatmaps, channel attribution, A/B test calculators, and competitive feature matrices.

10 min readView Project
View All Projects
04
Experience

Natixis (Natixis Corporate & Investment Banking)

AI Risk Analytics Intern

01/2025 – 07/2025
  • Metrics framework & instrumentation: Decomposed KYC/compliance processes into funnel stages (submission -> acceptance -> review -> supplementary -> approval/rejection), defining throughput, SLA, backlog, and anomaly rate metrics to support "identification -> strategy adjustment -> review" cycles.
  • Automated data pipeline (3,000+ lines of code): Multi-source data cleaning, validation, and scheduled refresh, supporting daily reports and anomaly tracking, reducing ~20% manual operations.
  • Observability dashboard (Power BI): Designed drill-down paths by region/product/channel/reason code with threshold alerting, enabling R&D, operations, and compliance teams to collaborate around a unified fact table.
  • AI workflow monitoring loop: Established "metric definition -> anomaly detection -> root cause analysis -> retrospective review" workflow, strengthening productized understanding of rule monitoring, data feedback mechanisms, and process optimization strategies.

GE Vernova

Finance Digital Audit Intern

09/2024 – 01/2025
  • Report productization: Excel modeling + VBA automation for forecast/operations reports (version control, metric validation, anomaly alerts), reducing errors and improving delivery stability.
  • Process governance & controlled rollout: Mapped data integrity, authorization approval, and audit trail risk points, producing remediation checklists and execution steps (corresponding to payment link canary/rollback/audit tracking).
  • Modular analysis: Decomposed variance analysis into reusable templates (driver decomposition, sensitivity, scenario comparison), improving growth/commercialization analysis efficiency.

Allinpay Payment Fintech

AI Risk Product Manager & Business Analyst Rotation

07/2022 – 02/2023
  • Product iteration: Assisted in upgrading YunShangTong (2021 Shanghai Fintech Innovation Regulatory Sandbox Project), driving "business-finance integration" digital transformation, coordinating business and financial requirements, planning transformation roadmap and driving system API development, completing core module alignment (30% of total tasks), improving cross-department response efficiency by over 35%.
  • Trained and fine-tuned financial risk control models using knowledge graphs and Graph Neural Networks (GNN), combining MetaPath, community detection, and GNN algorithms to uncover complex risk relationships, deployed in anti-fraud, AML, and intermediary fraud detection scenarios.
  • Report writing: Independently prepared and presented 12 industry briefings to the Board, covering policy analysis, trend tracking, and industry forecasts, plus 5 special reports (cross-border payments, digital finance, etc.), providing data-driven strategic recommendations to senior management.
  • Regulatory draft research: Managed card organization relations (UnionPay), participated in cross-border payment and digital RMB research, led drafting of "QR Code Payment Interim Regulations" based on policy analysis and international case studies, providing research evidence for institutional development.

Caizhen Securities Co., Ltd.

Risk Control Intern

01/2022 – 03/2022
  • Assisted in financial statement risk identification and compliance review, investigating potential risk areas around revenue recognition, inventory valuation, and cash flow to support project risk assessment.
  • Compiled risk identification and assessment reports, summarizing key risk issues and improvement recommendations to support internal reporting and follow-up remediation.
05
Education
09/2023 – 12/2026 (expected)

EDHEC Business School

Master in International Finance & Management (Dual Degree)

GPA 15.66/20 (Top 15%) | Outstanding Chinese Alumni Scholarship (50% tuition)

Core Courses

Python Portfolio Analysis, Fintech, Financial Modeling, VBA, M&A Analysis, Financial Analysis, Climate Change Science & Economics

09/2018 – 06/2022

Shanghai Jiao Tong University

BSc Finance (Minor: Information Management)

Core Courses

Business Statistics, Database & Big Data, Data Collection & Visualization, Computational Text Analysis, Algorithm Analysis & Design, Operations Research, AI Fundamentals, Econometrics, Fixed Income Securities, Securities Investment Analysis, Venture Capital & Financial Innovation, Financial Engineering, Corporate Finance

06
Skills

Analytics & Data Tools

Python90%
SQL86%
Power BI80%
ECharts / D375%
R65%
Top: Python·90%

AI / LLM Engineering

Prompt Engineering90%
RAG & Retrieval85%
LangChain / LangGraph80%
ML Modeling72%
Vector Databases75%
Top: Prompt Engineering·90%

Finance & Risk

Financial Analysis90%
Risk Modeling86%
Regulatory Compliance82%
A/B Testing & Stats78%
Statistical Inference76%
Top: Financial Analysis·90%
07
Activities & Leadership

EDHEC Campus Ambassador & Chairman, Chinese Society

09/2023 – 06/2026

Raised €2,000 in sponsorship and organized the Spring Festival Gala with 200+ attendees. Led outreach campaigns for prospective Chinese students and served as official EDHEC Campus Ambassador.

Open to Collaborate

Let's work together

Whether it's an AI engineering project, financial analytics, or a new opportunity — I'd love to hear from you.

longyu.xu@edhec.com