Sean
Nguyen
Supporting IT operations. Automating repetitive workflows with control.
Resolving operational bottlenecks by connecting tools, automating manual tasks, and keeping human oversight.
- HTML · CSS · JavaScript · PHP
- TypeScript · Python
- Workflow orchestration
- Webhooks & APIs
- Structured outputs · Validation
- OpenAI · Claude · Gemini
- Human-in-the-loop
- Multi-agent handoff
- Document extraction
- Audit trails
About
Sean Nguyen (Nguyen Lu Dai Son)
Location
Ho Chi Minh City, Vietnam (GMT+7)
Specialization
IT Operations, Workflow Automation & Next.js
Availability
Open for full-time, remote & project roles
I combine hands-on IT operations experience with modern workflow automation to solve real business bottlenecks.
In IT operations and application support, I focus on system reliability, user troubleshooting, and issue tracking. My background at DXC Technology trained me to understand real end-user problems, log clear defects, and maintain mission-critical software.
In workflow automation, I build web tools using TypeScript, Next.js, and REST APIs. I connect tools via webhooks, automate repetitive document and data tasks with AI, and put review queues in place so teams always remain in full control.
Practical Operations
Rooted in real-world application support, defect tracking, and user troubleshooting.
Modern Automation
Connecting tools with clean APIs, webhooks, and structured, validated data.
Clear Communication
Explaining technical system details clearly to business users and technical teams alike.
Disciplined Delivery
Every automated workflow includes audit logs and human review checkpoints.
How I turn manual work into automated systems
From identifying operational bottlenecks to delivering an automated, easy-to-run system.
- 01
Spot the problem
Identify manual support tasks, data rekeying, or operational bottlenecks.
- 02
Map the process
Define system inputs, logic rules, exception paths, and output targets.
- 03
Build the automation
Connect APIs, webhooks, or AI steps to handle high-volume repetitive tasks.
- 04
Add human controls
Set up approval steps and audit logs for sensitive actions and edge cases.
- 05
Deploy & document
Deliver clear operational docs and handover to ensure your team is in full control.
Systems that do real work
Click any demo to open it. See how manual work becomes software: AI drafts the work, people stay in control, and every step is easy to check.
CRM ↔ Slack Integration Bridge
Webhook event in → AI summary → CRM note + Slack channel post with action buttons.
Preview of CRM note and Slack message with edit and skip controls before any push.
Live: Live LLM summary from webhook JSON to structured CRM note and Slack message preview in the app.
Note: CRM and Slack destinations are mock payloads. No real HubSpot or Slack API calls, no OAuth, no persistent delivery.
Receipt & Document Agent
Upload a receipt or PDF → extract vendor, date, amount, lines → validate → exception queue.
Structured fields with validation and exception queue for human review.
Live: Live structured LLM output returning typed fields with per-field confidence. File parse runs in the browser, no server storage.
Note: No real OCR pipeline or accounting system push. Validation and downstream bill creation are simulated.
Studio Knowledge & Asset Desk
Studio docs in → keyword chunk search → grounded answer with citations + permission gate → OneDrive/DAM next actions.
Grounded answers with citations and permission-aware next actions for review.
Live: Live grounded answer with citations over keyword-scored chunks. Permission gate enforced in UI.
Note: Retrieval is keyword scoring over mock docs, not vector search. No OneDrive, SharePoint, or DAM connection. Vector RAG is planned, not live.
For: Creative studios, design ops, marketing teams using Adobe CC + OneDrive
Multi-Agent RFI Desk
Missing info detected → RFI drafted → reply tracked → case updated, with escalation paths.
Case state with detection, drafting, and tracking steps plus human escalation.
Live: Live multi-agent workflow with shared case state. Detector, drafter, and tracker run as separate LLM steps with handoff contracts.
Note: Email and Slack notifications are mock shapes. No real inbox or channel integration.
Transaction Coding Agent
Bank lines in → suggested accounts, tax codes, and confidence → accountant Approve / Edit.
Suggested coding with confidence scores, review queue, and activity log.
Live: Live structured LLM output with account, tax, confidence, and rationale. Review queue and audit log run in the app.
Note: Ledger destination is mock. No real Xero or QBO connection, no OAuth, no posting.
Experience
Application support foundation combined with modern workflow automation and software delivery.
2023-Present
IT Operation & Workflow Automation Engineer
Independent
Building internal web tools and operational automations with Next.js, TypeScript, and REST APIs. Connecting tools via webhooks, setting up structured review queues, and creating clear audit trails so operations teams can run with confidence.
2020-2023
Application Support Engineer
DXC Technology
Maintained, tested, and installed a pharmacy management application for DXC clients. Checked existing features, logged defects, supported fixes, and helped customers go live.
2019-2020
IT Engineer
TMA Solutions
First year after graduation. Software and IT delivery in a product-engineering environment: requirements, implementation discipline, and shipping working software with the team.
Skills
Clear across two pillars: maintaining reliable system operations and building controlled workflow automations with Next.js, APIs, and human review.
Frontend & UI
- Next.js 16 · React 19 · TypeScript
- Tailwind CSS · Responsive webapps
- Performance & UX basics
Backend & APIs
- REST APIs · Webhooks · Next.js API routes
- Python · Postgres / Supabase · Redis
- Data validation & JSON schema
IT Operations & Support
- Application support & user troubleshooting
- Defect logging & root cause analysis
- System uptime & SLA monitoring
Workflow Automation
- Automated request intake & exception queues
- Document extraction (OCR / Vision LLMs)
- CRM & Slack/Email notification patterns
Security & Reliability
- Human-in-the-loop review checkpoints
- Audit trails & decision logging
- Input validation & rate limiting
Tools & Infrastructure
- Cursor · Claude Code · VS Code
- Vercel · GitHub · Upstash Redis · Helpdesk tools
Education & certificates
FPT University, Bachelor of Software Engineering
Software engineering · 2015-2019
Graduated 2019
English, TOEIC
Score 895 / 990
Certificate
Japanese, JLPT N4
Language certificate
Certificate
Work with me
Hiring in 3 steps
No pitch decks. You describe the painful workflow, I show a working slice on your data, then we ship with docs your team can run.
Tell me the costly loop
One call or message about the manual work burning time. I reply within 24 hours with what to automate and what stays human.
See a working slice
A live demo on your data, not slides. You click it, edit it, and check every result before anything ships.
Ship with handover
Docs, review gates and audit trail included. Your team runs it without me after handover.
Start with one message
Fill this in and hit send. It lands straight in my Telegram. Prefer chat? Message on Zalo or WhatsApp instead.
- Reply within 24 hours
- Working slice on your data
- Docs, review gates and audit trail
Let's build reliable operational systems
Open to roles where you need someone who understands hands-on system operations and can build automated tools to eliminate manual bottlenecks.