AI strategy & data scienceAI 策略與資料科學

I help businesses rigorously assess actionable AI solutions and their ROI.我協助企業精準評估AI落地方案及投資價值。

Specializing in data science and AI consulting, I adhere to one core principle: every model must be built to drive tangible business decisions. Currently writing about AI strategy, data science project, and technical team leadership.專注於資料科學與 AI 顧問服務,我始終堅持一個核心:每一個模型都必須為了驅動實質的商業決策而生。這裡記錄了我對 AI 策略、資料科學專案評估方法與技術團隊領導實務。

Recent posts最新文章

All posts全部文章
From RAG Prototype to Deployment Decision: A CFPB Case Study
Gen AI生成式 AI15 Jul 20262026年7月15日

From RAG Prototype to Deployment Decision: A CFPB Case Study從 RAG 原型到部署決策:CFPB 案例研究

A practical guide to designing and evaluating RAG through a LangChain complaint-triage case study—and deciding why the prototype is suitable for a controlled analyst-assistance pilot, but not autonomous deployment.本文透過一個以 LangChain 建構的申訴分流案例,說明如何設計與評估 RAG 系統,以及為何這項原型適合進入受控的分析師輔助試點,卻尚不足以支援自主部署。

38 min read閱讀約 66 分鐘

LLM Fine-Tuning: Teaching a Small Model to Analyze 10-K Risk Disclosures
Gen AI生成式 AI1 Jul 20262026年7月1日

LLM Fine-Tuning: Teaching a Small Model to Analyze 10-K Risk DisclosuresLLM 微調:教小型模型分析 10-K 風險揭露

A practical guide to supervised fine-tuning, PEFT, LoRA, and QLoRA—covering dataset design, loss masking, leakage-resistant evaluation, and a hands-on experiment with SEC 10-K risk disclosures.一份關於監督式微調、PEFT、LoRA 與 QLoRA 的實用指南,涵蓋資料集設計、損失遮罩、可防資料外洩的評估方法,以及一項以 SEC 10-K 風險揭露為題的實作實驗。

23 min read閱讀約 44 分鐘

LLM Serving: Continuous Batching, Distributed Execution, and Service-Level Objectives
Gen AI生成式 AI26 Jun 20262026年6月26日

LLM Serving: Continuous Batching, Distributed Execution, and Service-Level ObjectivesLLM 服務部署:連續批次處理、分散式執行與服務等級目標

How do you serve 10,000 concurrent users? A deep dive into continuous batching, disaggregated prefill architectures, and multi-GPU parallelism to meet strict Service-Level Objectives in production, plus a troubleshooting quick-reference.要如何同時服務一萬名並發使用者?本文深入探討連續批次處理、分離式預填充架構,以及多 GPU 平行化,說明如何在正式環境中達成嚴格的服務等級目標,並附上疑難排解快速參考。

16 min read閱讀約 24 分鐘

Selected projects精選專案

All projects全部專案

Engineered a AI-powered talent-recommendation system that cut staffing search to minutes開發 GenAI 人才推薦系統,將專案人力搜尋縮短至數分鐘

Designed the retrieval, model-selection, and evaluation layers of a RAG system that helped managers identify evidence-backed candidates across an 8,000-person consultancy.設計 RAG (檢索增強生成) 系統的檢索、模型選擇與評估層,協助專案經理在一家擁有 8,000 名員工的顧問公司中,找出最合適人選。

Global Consultancy · AI Engineer · 2024-2025跨國顧問公司 · AI 工程師 · 2024-2025

View project查看專案

Staffing search: days → minutes專案人力搜尋時間:從數天縮短至數分鐘

Award-winning transaction monitoring system for a financial institution為金融機構打造的防洗錢交易監控系統,榮獲獎項肯定

Built and shipped a production monitoring system from an undefined brief with no labelled data — later named “Best AML/CFT Data, Analytics & Visualisation Solution” at the Regulation Asia Awards for Excellence 2023.在需求未明、亦無標註資料的情況下,打造一套正式運作的交易監控系統,其後在《2023 Regulation Asia Awards》中榮獲「最佳洗錢防制/打擊資恐 (AML/CFT) 數據、分析與視覺化解決方案」獎項。

Financial Institution · Lead Data Scientist & Full-Stack Developer · 2022-2025金融機構 · 首席資料科學家暨全端工程師 · 2022-2025

View project查看專案

Regulation Asia Awards 2023Regulation Asia Awards 2023

Need clarity on where AI can create real value — and what is actually worth building?想釐清 AI 能在哪裡創造實際價值,以及哪些方案真正值得投入嗎?

Get in touch與我聯絡