Hilmy Izzulhaq
work

Systems in production, and how they were built.

Three case studies in depth, then the rest of the deliveries. Client names appear only where they are cleared.

Plate recognition for Korlantas Polri

case study 1: computer vision, on-premise

Part of Percik, the platform for vehicle registration and compliance checks run by the Indonesian National Police Traffic Corps. Plate recognition and vehicle identification across 5 sites nationwide.

Accuracy
98.7% plate reading in live operation, measured on a human-checked sample of live reads
Deployment
Fully on-premise, on Proxmox/KVM virtualization I operated. No cloud.
Models
I trained the plate models and the detector and reader for metal-stamped VIN and engine numbers, including tamper detection for re-stamped or ground-off numbers.
Field team
21 people (staff and contractors) in 7 teams of 3, SOP-driven daily reports, weekly coordination
Validation
Held-out test sets and client acceptance tests before go-live; live accuracy tracked and models retrained on site data afterwards
what made it work

A plate reader that scores well on a test set can still fail in the field. The reads that mattered were the live ones, so accuracy was measured on human-checked samples of real traffic at the sites, and the models were retrained on what the sites actually saw.

Stamped VIN and engine numbers are harder than plates: low contrast, rust, paint and deliberate tampering. The reader flags numbers that look re-stamped or ground off.

Faces and uniform insignia are blurred.

Access control and daily health screening at an Indonesian refinery

case study 2: 2022, still in operation in 2025

Delivered by PT Adhya Arutala Amerta jointly with ARSA Technology, as a subcontractor under a main contractor. I led the 33-person team end to end: needs discovery, solution design, implementation, deployment and after-sales.

It screens about 10,000 employees and contractors. The final gate opens only when every check has passed:

  1. Five bare turnstiles, retrofitted with a computer, screen, camera and software: a card tap plus face verification.
  2. Ten custom-built self-service health kiosks: a camera-based Romberg balance test, blood pressure, heart rate, oxygen saturation and body temperature, each result tagged to the person by face.
  3. A 16-zone walk-through metal detector, extended with a computer, face recognition and a screen showing where a metal item was found.
  4. The final turnstile: a card tap.

The site has no internet access, so the whole system runs offline. Two-way integration with Honeywell Pro-Watch, the site's access control and directory, was worked out in-house with no vendor support and no API documentation.

AI agents in production, on-premise

case study 3: private LLMs, RAG, agents

A self-hosted stack I built and run in my company's own operations: LLMs served with Ollama and vLLM, and RAG over SOPs, the product and price-list knowledge base, active projects and the full CRM pipeline.

Workflow automation drafts quotations and full solution proposals (timeline, UAT checklist, statement of work), runs price-margin-cost analysis, sends follow-up reminders, answers staff questions, summarises client messages and enforces process steps.

An MCP server gives AI agents the CRM, quotations and proposals, the product catalog, projects, meetings, SOPs and client message threads, with a human-approval step before anything reaches a customer, a calendar or an invoice.

staff time per task, before and after
Taskbeforeafter
Quotation5 h30 min
Solution proposal (timeline, UAT checklist, SoW)25 man-h3 man-h
Price-margin-cost analysis7 h2 h
Process enforcement5 man-h30 min

More deliveries

defense

Restricted-area protection, Ministry of Defense

Facial recognition and AI video analytics ("Arsaca Eagle Eye") for perimeter security and access control at defense facilities, for Pushansiber Kemhan RI. Classified-handling procedures applied.

product

ARSA Face SDK

I hand-coded the original Python codebase, then set the new architecture and rewrote it in Rust. 99.45% face verification accuracy on LFW (10-fold, end to end); the edge model scores 99.18% on LFW at 13 MB, with no GPU.

data

Offline ML data platform

An air-gapped in-house platform for labelling, dataset versioning and training, with a self-hosted vision-language-model pre-labelling tool. In use for about two years.

Industrial safety analytics

computer vision on existing CCTV, on-premise

PPE detection, activity recognition and heavy-equipment monitoring for multiple state-owned enterprises. The pictures below are ARSA's Basic Safety Guard product screens (demo data) and a frame from ARSA's demo footage.

ARSA AI Box series

product

An edge-AI platform that turns existing CCTV into real-time detection, fully on-premise. Productized for HSE compliance, traffic analytics, retail analytics and audience measurement.

Video analytics proof of concept, BRI (2023)

banking

A multi-function video analytics proof of concept for Bank Rakyat Indonesia at the Pondok Indah branch, Jakarta.

Hardware and embedded

RFID productivity terminal with an LCD and a 16-key keypad
One of about 150 RFID productivity terminals built for Busana Apparel Group (2020).
A production batch of terminal circuit boards laid out in trays
The production batch: firmware, hardware manufacturing and the backend were ours.
Close-up of a Rockchip single-board computer
The Rockchip board that ran the embedded voice-to-text engine for Botika (2019).
Terminal output in Indonesian showing on-device speech recognition with inference time
On-device speech recognition, logged on the board: listening, recording, inference, posting the text.
  • About 150 RFID productivity terminals for PT Ungaran Sari Garments / Busana Apparel GroupFirmware, hardware manufacturing, backend2020
  • Embedded voice-to-text engine for BotikaBuilt on Mozilla DeepSpeech2019
  • Automated industrial gate with long-range UHF RFIDFor a logistics operator in East Java
  • Radiology image analysis R&D at PT Adhya Arutala AmertaChest X-ray, CT/MRI; research and prototype stage only
  • Commercial Face Recognition APIPublished on RapidAPI