Open to opportunities · Brisbane, AU / Remote

I build fast, reliable backend systems — and practical AI products on top of them.

Senior Backend Engineer with 6 years of full-time experience building distributed systems, data platforms and backend services, plus recent freelance work in LLM, RAG and applied AI. I work mostly in Go, Node.js and Python, and I like turning slow, fragile services into fast, observable systems. Currently completing a Master of IT at QUT in Brisbane.

See case studies Download résumé
About

About me

I'm a software engineer with 6 years of full-time backend experience — starting with chatbot and NLU products, then moving into distributed systems and data platforms, and most recently extending that foundation into LLM-powered applications. Along the way I led a small engineering team at AmazingTalker and, more recently, took on part-time freelance projects across RAG, document processing and business systems.

What I care about most is the part users actually feel: speed, reliability, and whether things still hold up as they grow. I like taking something slow, fragile or messy and turning it into something fast, observable and easy for the next engineer to pick up — and I try to back decisions with real numbers rather than opinions.

Right now I'm completing a Master of IT at QUT in Brisbane, and most of my own time goes into AI agents and applied AI workflows — building things like an autonomous issue-to-PR coding agent and a tool that compiles raw notes into structured knowledge. I'm looking for backend, platform or applied AI roles where I can keep working where solid systems meet useful AI.

On the practical side: I'm based in Brisbane with current work rights, and no near-term employer sponsorship is required.

Work Experience

Where I've worked

6 years of full-time backend engineering, followed by part-time freelance work in applied AI and business systems.

Jul 2023 — Oct 2025Part-time Freelance · Taiwan
Freelance Backend / AI Engineer · Freelance
  • Built a RAG-based knowledge system for secure, document-grounded Q&A — with automated ingestion, vector search and per-user data isolation.
  • Developed an LLM-powered translation service that fully translates PDF, DOCX and other document formats while preserving structure.
  • Designed and built a CRM system that lifted revenue and improved customer retention.
  • Consulted and delivered a manufacturing project for an early-stage garment startup.
PythonLLM / RAGVector SearchGCPAWS
Mar 2021 — May 2023AmazingTalker · Taiwan
Senior Backend Engineer · AmazingTalker
  • Built a data warehouse and pipeline that cut report generation time by 90% and saved ~$10K/month, powering data-driven marketing decisions.
  • Built a shared data platform of reusable APIs across teams, cutting data-API development time by 80%.
  • Led a 3–4 person engineering team, setting standards and guiding feature and data projects.
  • Refactored the teacher-ranking search: 50% faster API responses, +10% engagement and +5K new monthly registrations.
  • Replaced a DB-based distributed lock with Redis, halving latency.
  • Designed a cloud solution with an AWS Lambda + S3 pipeline processing 1,000+ videos/day.
GoPythonRailsAWSTerraformAirflowRedisMySQLData EngAirbrake
Aug 2019 — Mar 2021WEI-PO Co., Ltd · Taiwan
Backend Engineer · WEI-PO Co., Ltd
  • Cut transaction latency by 80% by replacing the existing mechanism with RabbitMQ.
  • Introduced an EFK logging architecture, reducing application latency by 90%.
  • Applied Redis distributed locks to resolve critical transactional issues in a distributed system.
  • Rebuilt Dockerfiles with multi-stage builds and CI/CD — 80% smaller images, deploys from 30 min to 5.
GoPostgreSQLRabbitMQRedisDockerCI/CDEFK
Aug 2018 — Aug 2019Pentium Network · Taiwan
Backend Engineer · Pentium Network Technology
  • Integrated cloud assets (CDN, FQDN and more) across AWS, AliYun, Tencent and GCP for optimal resource use.
  • Designed a chatbot architecture with a conversational interface over an instant-messaging app.
  • Built a workflow framework to automate user tasks; used Kafka for event-driven, real-time processing.
Node.jsNeo4jKafkaAWSGCPKubernetesCDN
Apr 2017 — Jun 2018Lingtelli · Taiwan
Backend Engineer · Lingtelli Co., Ltd
  • Built the company's chatbot product, enabling fast bot deployment to Facebook and LINE in a few steps.
  • Developed a natural-language-understanding engine that powered the company's AI products.
  • Built an auto-scaling, CloudWatch-monitored system to keep services available under varying load.
PythonNLUAWSCloudWatch
Achievements

Selected case studies

A closer look at backend and data-platform work where system design moved product or operational metrics.

★ Highlight

Data warehouse & analytics pipeline

AmazingTalker · 2021–2023 · Go / Python / AWS
Problem

Marketing and product decisions were bottlenecked by reporting. Reports were slow to generate and expensive to run, and data was scattered across services with no single source of truth.

Approach

Designed and built a central data warehouse plus an ingestion pipeline, then exposed the data through reusable APIs so teams could self-serve instead of rebuilding the same queries.

Key decision

Invested early in a shared data platform rather than one-off reports. It cost more up front but removed duplicated work across teams and made every later project faster.

−90%
report time
~$10K/mo
cost saved
−80%
data-API dev time
★ Highlight

Teacher search & ranking optimization

AmazingTalker · 2021–2023 · Go / Search / Redis
Problem

Matching learners to the right teacher is the core of the product, but the ranking and search path was slow and wasn't converting browsers into sign-ups as well as it should.

Approach

Refactored how the teacher-ranking search retrieved and scored candidates, trimming work on the hot path so results came back faster and better-ordered.

Key decision

Treated API latency as a growth lever, not just an infra metric — faster, more relevant results fed directly into engagement and new registrations.

−50%
API response
+10%
engagement
+5K/mo
new sign-ups
Projects

Things I've built

Open-source side projects exploring applied AI, coding agents and developer automation.

Codex Cage
A practical way to bring agents into the SDLC without handing them your machine. Codex Cage takes a GitHub or Linear issue to a reviewed pull request: the implementation agent works inside a disposable Docker sandbox, runs the project's verification commands, scans the diff for leaked secrets, and sends the change through an independent read-only review. Only the host opens the PR once every gate passes.
TypeScriptDockerCodexCI/CDNode.js
View on GitHub →
Knowledge Compiler
A knowledge-management tool that turns raw, messy notes into structured knowledge. It uses an agent to find related notes by concept, propose merges, updates or new entries for human approval, and answer questions from the user's own knowledge base with citations. Built on the OpenAI Agents SDK with a clean-architecture Express backend and a React + Vite client.
TypeScriptOpenAI Agents SDKRAGExpressReactPostgreSQL
View on GitHub →
Meeting Manager action items board with AI-extracted follow-ups across To-do, In Progress and Done
AI Meeting Management Platform
A meeting-management platform built with a team as a current QUT industry project. Beyond scheduling and managing meetings, it uses an LLM to analyse meeting recordings and automatically surface action items and follow-ups — turning a raw recording into something the team can actually act on.
Node.jsPythonLLMTeam project
View live demo →
Skills

Technical skills

Languages & frameworks

  • Go
  • Node.js
  • Python
  • Ruby
  • Express
  • Rails
  • FastAPI

Databases & messaging

  • MySQL
  • PostgreSQL
  • MongoDB
  • Redis
  • RabbitMQ
  • Kafka
  • Data Engineering

Cloud & infra

  • AWS
  • GCP
  • Docker
  • Kubernetes
  • CI/CD
  • EFK

AI & QA

  • LLM / RAG
  • Vector search
  • API & Unit testing
  • Regression testing
Education

Education

Feb 2025 — PresentBrisbane, AU
Master of Information Technology · Queensland University of Technology
2011 — 2015Taiwan
B.Sc. Computer Science · National Taiwan University of Science and Technology
  • GPA 3.92 / 4.0

Hiring for backend, platform or applied AI work? Let's talk.

[email protected]