Nils Liu / Head of AI

Applied AI leader
for production
GenAI in finance.

Head of AI at AAA, building the AI function from the ground up and leading a mortgage AI review platform on Encompass data. Previously shipped bank-scale GenAI and agentic AI platforms from architecture to adoption.

96%
AI Coach CSAT
6
AI system patents
#1
bank GenAI platform
Applied AI Leadership Profile
Leadership track record
Nils Liu
Nils Liu
Head of AI / Agentic AI / Financial platforms

Open to senior Applied AI / GenAI platform roles

AI function buildout, agentic workflows, data foundations, and regulated production delivery

96%
AI Coach CSAT
6
AI system patents
#1
bank GenAI platform
Agent delivery flow
Evals on
Retrieval01
GraphRAG / ontology
Governance02
policy / PII / roles
Agent workflow03
planner / tools / evals
Human review04
audit trail / handoff
AI Agent Architecture (Financial Institutions)·Multi-Agent System Design·Financial Compliance AI (GRC)·RAG / GraphRAG·LLM Product & Platform Design·GenAI Platform Architecture·Enterprise Knowledge Management·Cross-border Fintech Deployment·Evaluation-Driven AI Development·Patent Holder (6 Granted, LLM Systems)·Conference Speaker (7 Talks)·GCP Serverless / Cloud-native

Impact in Numbers

Not a feature list. Real outcomes shipped in production.

#1
First Production GenAI at a Leading Bank
Launched August 2024, serving thousands of bank staff.
96%
AI Coach Satisfaction
3-layer Agent architecture with GraphRAG and Rubrics-based evaluation.
6
AI Patents Granted
Sole inventor on all 6. 2 additional invention patents under review.
7
Conference Talks
iThome Hello World 2024+2025, DevFest Taipei 2025.
Weeks
PoC to Production
Zero to live in a regulated financial environment.

Global Trajectory

2006–2010

NTU — B.Sc. Chemistry

Graduated from National Taiwan University, building a rigorous scientific foundation.

2012–2015

TU Chemnitz — M.Sc. Chemistry

Pursued a Master's degree in Germany, gaining international academic and cross-cultural experience.

2016–2017

Groningen Univ. Visiting Researcher / Fraunhofer Intern

Conducted advanced materials and nano-synthesis research at a Nobel Laureate lab (Holland) and Fraunhofer (Germany).

2017–2019

Avancis GmbH — Int'l Project Specialist / PM (Germany)

Managed tech-transfer projects and pilot-line implementations, coordinating cross-border teams for automation acceptance.

2019–2022

DBS Bank — MA → DevOps Sr. Associate

Joined via Management Associate program. Led Python automation and ML enablement for 200+ staff.

2023–2024

Synpulse — Banking Tech Consultant

Consulted at a Swiss financial advisory firm; built the GenAI risk analytics module 'Narrator'.

2024–Present

Cathay United Bank — GenAI Product Manager / Solution Architect

Led production GenAI and agentic AI platforms for financial-services users: CathayGPT, AI Coach, and the overseas AI Agent platform. Owned solution architecture, rollout, governance, and measurable adoption.

2026–Present

AAA Lendings — Head of AI

Building AAA's AI function from the ground up. Leading a 3-person engineering squad to deliver an end-to-end mortgage AI review platform on Encompass data, covering document intake, extraction, validation, review workflow, and submission / underwriting handoff.

Featured Prototypes

Selected production AI and agentic workflow examples.

AI KYC Agent — Autonomous Browser Automation

AI KYC Agent — Autonomous Browser Automation

An AI Agent that controls the browser like a human to perform KYC verification — fully autonomous, fully audited.

Autonomous Agent

AI controls the browser like a human operator — zero manual intervention required.

Full Audit Trail

Every action is recorded with screenshots and structured audit logs for compliance.

Auto-Generated Report

A structured KYC report is automatically produced upon task completion.

Compliance-Ready

Built for regulated environments — governance and observability from day one.

News Sentiment Agent Team — Multi-Agent Research

News Sentiment Agent Team — Multi-Agent Research

An AI Agent Team that breaks language and time barriers — users discuss news with AI, which automatically collects, summarizes, cites sources, and exports or emails reports.

Multi-Agent Collaboration

Agent team members work together and can be infinitely expanded for new capabilities.

Cross-Language Research

Break language and timezone barriers — discover and analyze global news in any language.

Interactive Q&A

Chat with AI to drill down into stories, uncover related news, and ask follow-up questions.

Auto Summary & Export

AI collects info, summarizes with sources attached, and exports or emails the final report.

Insurance Life — Into the Mist (Lead Dev: Yen-Min Chiu)

Insurance Life — Into the Mist (Lead Dev: Yen-Min Chiu)

A life simulation system that visualizes risk management and financial planning, mapping life's unexpected events to actual insurance claim logic.

Risk Visualization

Pre-warns of life events (like accidents or illness) so players can plan their safety nets in advance.

Actuarial Mapping

Dynamically maps unexpected events to real-world healthcare and insurance payout results.

Dynamic Age Engine

Accurately simulates changing income, family responsibilities, and risk probabilities over time.

Interactive Financial Education

Breaks down jargon barriers to provide an interactive experience with real-world claim logic.

AI Interview Assistant — Live Google Meet Participant (Lead Developer: Sunny Sun)

AI Interview Assistant — Live Google Meet Participant (Lead Developer: Sunny Sun)

An AI Agent that joins Google Meet as a named participant, providing real-time interview support and automated meeting documentation.

Live Meeting Participation

AI joins Google Meet directly as a named participant — no plugins or screen capture needed.

Interview Workflow Support

Assists interviewers in real-time with structured scoring and summary feedback on candidates.

Auto Meeting Minutes

Automatically records the full conversation and generates exportable structured meeting summaries.

Multi-Interviewer Integration

Supports multiple interviewers simultaneously, synthesizing different perspectives and evaluations.

How I Work With Teams

Primary fit: senior AI leadership or applied GenAI platform roles. Advisory, prototyping, and enablement are supporting collaboration modes.

AI Leadership Advisory

Focused conversations

I help teams reason through AI platform decisions with an operator's view: what to build, what to buy, how to govern it, and how to ship it inside regulated environments.

Best for: AI leadership roles, platform strategy, regulated GenAI architecture

AI roadmap critique, architecture review, governance concerns, platform/team operating model, executive-level narrative.

Production-Grade Prototyping

2–6 weeks

I build focused prototypes to test the hardest parts of an AI workflow: data quality, tool contracts, evaluation, permissions, and human review.

Best for: proving an agentic workflow before scaling a team or roadmap

Working prototype, evaluation suite, cost model, technical handoff, demo recording.

Team Enablement

0.5–2 days

I run hands-on sessions around real platform work: RAG/GraphRAG, agent workflows, evals, governance, and production handoff.

Best for: upskilling engineering teams and internal AI product builders

Custom workshop, hands-on labs, reference materials, follow-up Q&A session.

6 AI Patents — The Stories Behind Them

Sole inventor on all six. Each patent originated from a real enterprise problem, not an academic exercise.

Sole Inventor
M670472

Financial Investment Advice Generation System

LLMs produced unstructured, unauditable investment recommendations. This patent enforces structured output that meets financial compliance requirements.

M671161

Intelligent Optimization System

Enterprise prompts were managed ad-hoc with no versioning. This patent establishes a version-controlled prompt optimization mechanism.

M671223

Information Query System

Traditional keyword search fails on unstructured enterprise documents. This patent introduces a semantic retrieval architecture for accurate information access.

M671449Invention Patent Pending

Customizable Generative AI System

Different bank departments needed custom AI behaviors on the same underlying model. This patent solves the multi-scenario deployment scaling problem.

M674713

Data Query System

Cross-system data queries were fragmented and costly to integrate. This patent provides a unified query interface to reduce engineering overhead.

M676680Invention Patent Pending

Knowledge Graph Construction System

Unstructured enterprise knowledge was inaccessible to AI systems. This patent builds a reasoning-capable knowledge structure so AI genuinely understands business context.

About

I'm Nils (劉岦崱) — an applied AI leader who builds AI Agent platforms that actually work inside financial institutions. I am currently Head of AI at AAA, building the company's AI function from zero and leading an engineering squad on an end-to-end mortgage AI review platform built on Encompass data. Before AAA, I led production GenAI and agentic AI platforms in banking: CathayGPT, AI Coach, and an overseas AI Agent platform. I hold 6 utility patents, all in LLM application system architecture. My focus is production, not demos: regulated environments, compliance constraints, and real users in real financial institutions.

Principles

The Bitter Lesson

Scale and compute win. I build systems that leverage foundation models rather than fight them.

Platform-First

One-off solutions don't survive. I design for reuse, governance, and team autonomy from day one.

Evaluation-Driven

If you can't measure it, you can't ship it. Rigorous evaluation is the foundation of every project I touch.

Stack & Skills

PythonSQLGCP (Cloud Run / Vertex AI)Serverless ArchitectureAgentic Workflows / MCPRAG / GraphRAG / Agents / EvalsReact / Next.js / TypeScriptLangChain / LlamaIndexPostgreSQL / Vector DBs

Credentials

Patents

6 granted (GenAI / Knowledge Graph / Data Query systems)

Award

1st Place — 2024 Enterprise Innovation Competition

Talks

iThome Hello World 2024 & 2025 (7 sessions), DevFest Taipei 2025

Certifications

PMP (Project Management Professional)

Education

NTU CS (MSc) · Quantic MBA · TU Chemnitz MSc · NTU BSc

Languages

Chinese (native), English, German, Japanese (basic)

For senior AI / Applied GenAI leadership roles, platform architecture work, or teams building AI in regulated environments, I'm open to a conversation. Advisory and speaking are welcome, but the main fit is hands-on AI leadership with measurable delivery.

Discuss Fit

Get in Touch

For senior AI / Applied GenAI roles, platform leadership, or focused advisory conversations, send a note with context.

Based in Taipei, Taiwan (GMT+8)