Portfolio — AI Automation & Workflow Engineering

Yuen
Wei Ling

I build AI-powered systems that replace manual, repetitive work — multi-agent pipelines, RAG architectures, automated data validation, and intelligent workflow orchestration.

Available for hire Singapore-based Python Claude API n8n Multi-agent systems
Scroll
01

Selected Projects

RAG · Document Intelligence

Multi-Document Contradiction Detector

A RAG pipeline that ingests multiple PDF documents simultaneously and surfaces factual contradictions across them — tested on real DBS quarterly financial reports. What analysts spend hours cross-checking, the system flags in minutes, with a built-in chatbot for follow-up interrogation.

19 Critical discrepancies found
95 Pages processed
3 Real DBS reports tested
Anthropic Claude API ChromaDB RAG Python Streamlit pdfplumber Pydantic sentence-transformers
View on GitHub
Automation · Job Intelligence

AI-Powered Job Application Tracker

A fully automated job sourcing system that scrapes 150+ Singapore listings daily across MyCareersFuture, LinkedIn and JobStreet, scores each against a candidate profile using Claude API, routes high-relevance matches to Airtable, and delivers a curated daily digest. Distinguishes genuine AI tool roles from roles that merely mention AI in passing.

150+ Listings scraped daily
~2 hrs Manual search time saved
5–12% Genuine match rate (7+ score)
Anthropic Claude API n8n Airtable MyCareersFuture API JSearch API Gmail JavaScript
View on GitHub
Multi-Agent · Data Validation

Multi-Agent Data Validation System

A 4-agent pipeline that takes raw data through ingestion, rule-based checks, and Claude-powered anomaly detection — catching the class of errors that Excel formulas and conditional formatting systematically miss. Outputs a structured Excel report. Replaces approximately one hour of intensive manual review per run.

4 Specialised agents
~1 hr Manual review replaced
0 Edge cases missed by rules
Anthropic Claude API Multi-agent Python Pydantic OpenPyXL
View on GitHub
ETL · ESG Data Engineering

Automated ESG KPI Extraction Pipeline

An end-to-end pipeline that extracts structured ESG KPI data from PDF sustainability reports, loads it into SQLite, and surfaces it in Tableau dashboards — eliminating manual copy-paste from analyst workflows and enabling consistent, repeatable data collection at scale.

100% Automated extraction
0 Manual copy-paste steps
PDF→DB Full pipeline coverage
ETL Pipeline Python Camelot Pandas SQLite Tableau
View on GitHub
MCP · ESG Data Engineering

ESG Extraction Pipeline V2

A rebuilt version of the ESG KPI extraction pipeline with MCP integration — enabling richer tool use, smarter document routing, and deeper structured output from sustainability reports.

In progress
Coming soon

Next Project

More automation and AI tooling projects in the pipeline. This space gets updated regularly — check back or follow on GitHub.

Follow on GitHub
02

Technical Skills

AI & Automation
  • Anthropic Claude API
  • Prompt engineering
  • Multi-agent systems
  • RAG pipelines
  • ChromaDB (vector store)
  • n8n workflow automation
  • Airtable
Languages & Frameworks
  • Python (Pandas, Pydantic)
  • SQL
  • JavaScript (n8n nodes)
  • Streamlit
  • Excel VBA macros
  • Git / GitHub
Data & Integration
  • ETL pipelines
  • REST APIs
  • Data validation
  • SQLite
  • Tableau
  • OpenPyXL / Camelot
  • pdfplumber
03

Credentials

Full Anthropic Academy Curriculum
Claude API · MCP · Subagents · Agent Skills · Claude Code · AI Fluency
AWS Solutions Architect Associate
Amazon Web Services
Google Data Analytics
Google
IBM Data Analysis with Python
IBM / Coursera
JLPT N2 — Japanese Language Proficiency
Japan Foundation
Diploma in Infocomm & Digital Media (Merit)
Temasek Polytechnic
BBA — Bachelor of Business Administration
Ritsumeikan Asia Pacific University

Let's Build Something.

Open to AI automation, workflow engineering, and process automation roles in Singapore.