Full-stack × AI systems
Full-stack engineerputting LLMs intoreal products.
Scroll
Now
Full-stack engineer at Kite Metric, building client products in AI/LLM, fintech and enterprise software. Focused on making LLM workflows dependable: async jobs, authorization and multi-tenancy.
Selected work
01 — 3 projects · 2023 — now- 01
AI Interview Agent
AI voice interviews and structured candidate reports, so recruiters review a recommendation instead of starting from scratch.
→ ~150 candidate applications through one client deployment
- OpenAI
- Gemini
- n8n
- Vapi
- Next.js
- 02
Audit-Grade AI
An AI platform for audit and compliance work. I extended the pipeline that turns documents into annotated datasets for small-language-model training, and built the annotator qualification module.
→ Lower LLM processing cost through batch API requests
- FastAPI
- React
- Next.js
- PostgreSQL
- LlamaIndex
- 03
Car Care Platform
Booking and garage management for customers, merchants, staff and admins in one system.
→ Top 10 of 50 entries in a large-company competition
- React
- NestJS
- Supabase
- Tailwind CSS
Off the clock / In the lab
Personal projects.
Real curiosity.
A space for things I build for myself. First up: Sayso, turning the YouTube videos I love into English I can actually use.
Enter the lab
001 / Sayso 
Product-minded engineering
I turn rough conversations intoproducts people can actually use —shaping the experience, architectureand the intelligence behind it.
- 3+
- years shipping production software
- 4
- clients worked with directly, requirements to release
- 3
- domains shipped in: AI/LLM, fintech and enterprise
- 3.6
- GPA · Excellent degree, VNU-HCM University of Science (2025)
Honors
- B.Sc. IT with Excellent degree — VNU-HCM University of Science2025
- Binh Dinh Fellowship Scholarship2022
- Ranked 1st, Faculty of IT — K20 cohort2020
How I work
03 — Process- 01
Listen
Sit with the client, map the real workflow, and write down what “done” means before any code exists.
- 02
Architect
Turn requirements into a schema, service boundaries and an honest plan for where the LLM belongs — and where it doesn't.
- 03
Build
Own the feature end to end: UI flows, API, database and the deployment that puts it in front of users.
- 04
Harden
Make it survive reality — async workflows instead of fragile webhooks, traceable AI decisions, boring deploys.
Experience
04 — Career / 2020—NowA career built by taking on more of the problem.

- Aug 2024 — PresentHo Chi Minh CityCurrent chapter
Kite Metric JSC
Full-Stack Engineer
- Core engineer on concurrent client engagements in AI/LLM, fintech and enterprise software, working directly with product owners, business analysts, advisors and clients.
- Clarifies loosely defined requirements, agrees the design, then builds, ships and maintains it — including the engineering that makes LLM workflows dependable: async jobs, authorization and multi-tenancy.
- Apr 2023 — Aug 2024Ho Chi Minh City
LEAP LLC
Full-Stack Engineer
- Built digital-transformation and B2B/B2C booking web platforms for multiple clients, replacing manual booking processes.
- Developed search, booking, ticketing and seller-management modules with Angular, Java Spring Boot, Docker and PostgreSQL.
- 2020 — 2025Ho Chi Minh City
University of Science — VNU-HCM
B.Sc. Information Technology · Excellent degree
- Graduated 2025 with an Excellent degree, overall GPA 3.6 / 4.0.
- Ranked 1st in the Faculty of IT, K20 cohort (2020). Binh Dinh Fellowship Scholarship (2022).
The toolbox
05 — Working set / 06 disciplinesTools change. The standard doesn't.
A practical stack for taking products from interface to infrastructure — chosen around the problem, not the trend.
- 01
Frontend
Interfaces & product flows
- React
- Next.js
- Angular
- Tailwind CSS
- 02
Backend
Services & system boundaries
- Node.js
- NestJS
- Python
- FastAPI
- Java Spring Boot
- 03
AI / LLM
Retrieval, agents & workflows
- OpenAI
- Gemini
- Anthropic
- RAG
- LLM agents
- LlamaIndex
- n8n
- Vapi voice agents
- 04
Data
State & system of record
- PostgreSQL
- Supabase
- 05
Delivery
Build, ship & deploy
- Docker
- GitHub Actions
- Vercel
- AWS (basic)
- 06
AI-assisted dev
Drafts by AI, reviewed by me
- Claude Code
- Codex
- Cursor
Writing
- 01

Webhooks time out. LLM workflows don't care.
Why long-running LLM evaluations broke behind synchronous webhooks, and the async pattern that fixed it.
- 02

Designing one platform for four kinds of users
What building a garage booking system for customers, merchants, staff and admins taught me about schema-first product work.



