Yuelin Liu · Melbourne · Full-Stack Developer · AI & LLM Applications

I build reliable full-stack software, with a focus on AI/LLM applications and developer tools.

I work across product UI, APIs, authentication, data workflows and model-integrated features—turning messy requirements into reliable software.

Download Resume Contact

LinkedIn GitHub Writing

Selected Work

Marshal

A self-hosted job-application workspace for laptop and phone: capture a job ad, check the fit, draft material that only says what I can back up, and track each application to an offer.

Designed and built end to end · Personal project · 2026 · Pre-alpha · Private repository

Rebuilds the ideas proven in my Mac-only Dispatch tool as one private instance that my own devices reach over Tailscale, with no public port. Designed to be shared: each person runs their own copy with Docker and their own API key, so nobody hosts anyone else's data.

Stack · TypeScript · React / Vite · Node.js · Docker

Read case study

Job Search Dispatch

An AI-powered job-search workspace for assessing opportunities, preparing tailored applications and keeping every next step organised.

Designed and built end to end · Personal project · 2026 · Private repository

Connects captured job ads with saved experience to assess fit and draft application materials, including cover letters—without repeatedly rebuilding context in an AI chat. Job ads arrive through a guarded headless fetch or a browser extension, the Writer runs on bring-your-own-key providers or a signed-in Codex or Claude subscription, and application progress and follow-ups stay together.

Stack · React / Vite · TypeScript · Node.js · LLM APIs

Read case study

DSH Conversation Exporter

Exports full DeepSeek Harness conversations or selected whole turns as clean Markdown for reading, Git and cross-assistant handoff.

Built and packaged as a DSH Web plugin · 2026

Preserves Markdown and Unicode, keeps selective turn handling bounded, and excludes reasoning, tool activity and runtime metadata from exports.

Stack · JavaScript · Node.js · DSH plugin APIs · Markdown

Read case study Source

MoneyGuard

Turns a timecard photo into a weekly wage, spending and surplus audit.

Designed and built the end-to-end pipeline · 2026

Keeps ledger calculations local, validates model-generated OCR with Zod, and streams audit prose through separate providers.

Stack · TypeScript · Node.js · Gemini LLM · DeepSeek LLM

Read case study Source

More Engineering Work

AI HarnessCurrent work
GitHub-native AI-assisted engineering workflow built around NEXT → IMPLEMENT → ACCEPT → SHIP, exact PR-head SHA acceptance, deterministic verification and explicit human approval.
Melbourne University Ultimate Club Platform
Revisited a Next.js/MongoDB application to centralise server-side authorisation and turn authentication and write-path defects into regression tests and CI.
Client Data Delivery Validator
Python/pandas validation workflow for synthetic client-delivery CSV data with structured validation results and 12 pytest regression cases.

Experience

Hands-on development across prospective-client prototypes and an early-stage AI SaaS codebase, focused on working implementations, API integration and diagnosing inherited workflows.

Independent Developer

Prospective Client Demos for a Melbourne Consultancy

Sep 2025 - Present

Melbourne, Australia

Build demonstration applications for prospective clients, including a specialty coffee retailer and a drone training provider, translating informal briefs into working prototypes for business pitches.
Implement authenticated, database-backed prototypes with Next.js 15 App Router, Clerk OAuth and Convex as requirements become clearer.

Next.js 15 App Router · Clerk OAuth · Convex

Full-Stack Developer

ByteCroniX — Early-Stage AI SaaS

Mar 2025 - Jun 2025

Melbourne, Australia

Implemented OpenAI function-calling flows in a Node.js/Express codebase for AI-assisted product interactions.
Added timing instrumentation to an inherited points-summary path and identified current/proposed scoring services as the dominant latency contributors.
Profiled an inherited points-summary pipeline and parallelised independent service calls, reducing an observed local integration-test response from 26.7s to 5.6s.

Node.js · Express · OpenAI Function Calling · Docker/Postman Integration Testing

How I Build

I make the workflow concrete, measure what is actually happening, and turn fragile assumptions into explicit checks.

I start with the workflow, not the feature.

I turn an unclear problem into a concrete working flow before adding abstraction, polish or extra infrastructure.

Built prospective-client prototypes for a specialty coffee retailer and a drone training provider from informal business briefs.
Connected job capture, evidence-based triage, document review and follow-up in Job Search Dispatch, with saved application progress and manual submission.

I measure before I optimise.

I instrument inherited behaviour, trace where time or state is actually going, and change the smallest layer that explains the problem.

Instrumented ByteCroniX's inherited points-summary path, identified scoring services as the dominant latency contributors, then parallelised independent calls.
Revisited Melbourne Ultimate, traced silent session-role failures to fragmented authentication usage, and centralised session reads behind one database-verified guard.

I turn assumptions into enforceable boundaries.

I prefer schemas, explicit write rules and regression checks over relying on UI conventions, model behaviour or code-review memory.

Restricted Job Search Dispatch drafting to confirmed, permitted evidence and added validation, bounded repair and failure diagnostics before a generated letter replaces saved work.
Turned Melbourne Ultimate authorization and mass-assignment findings into automated regression tests and CI checks.

Product UI: React 19 · Next.js 15/16 · TypeScript · Tailwind CSS
APIs & Data: Node.js · Express · REST APIs · MongoDB · Convex
Auth & Delivery: Clerk OAuth · NextAuth · GitHub Actions · Docker · Vitest
AI & Validation: OpenAI Function Calling · Gemini · DeepSeek · Zod

Contact

I am based in Melbourne and open to full-stack software engineer opportunities. Email is usually the cleanest path for role details, interview scheduling and technical context.

Email: liuyuelintop@gmail.com
Phone: +61 451 690 105
Location: Melbourne, VIC, Australia

Email me directly LinkedIn profile

LinkedIn GitHub Writing

Prepare a role note

This opens a pre-filled email draft to liuyuelintop@gmail.com. It is intentionally lightweight so recruiters and hiring managers can start a real conversation quickly.