Moviq Indonesia UTC+7 · WIB
I build production-gradeAI products, computer vision, IoT systems, web platforms, data pipelines, cloud infrastructureend to end, edge to cloud.
Moviq is my independent engineering studio. You work directly with the engineer who designs, builds, and deploys your system — no hand-offs, no black boxes.
Featured work
Real systems in the real world — in production, in customers’ hands, and in front of judges. Each links to a full engineering case study.
All projects
PPE Monitor
Jul 2025 – Sep 2025
Production-deployed computer vision system for industrial safety at Pertamina facilities — full lifecycle from dataset curation to real-time dashboard.
94.2%
Detection Accuracy
AI-powered smart parking system using computer vision to detect vehicle presence in real-time, with edge computing and a live monitoring dashboard.
Hearth & Hair
Jan 2026 – Mar 2026
End-to-end service business web platform with automated booking, real-time calendar integration, and transactional email workflows. Shipped with real users.
About
Moga Taufiq Bagidya
Full-Stack & AI Systems Engineer · Moviq
Indonesia · UTC+7 · WIB
With a deep passion for AI systems and modern web engineering, I focus on bridging the gap between intelligent algorithms and real-world applications. I've shipped production computer vision systems, designed IoT backends, and built full-stack platforms — always driven by impact. From edge computing to cloud infrastructure, I build things that actually work. Let's create something extraordinary together.
Jan – May 2025
Best Project Award, FILKOM UB Technology Exhibition
Neopark: real-time parking occupancy from low-cost edge cameras — 94.2% detection accuracy and the most-visited booth.
Mar – Apr 2025
National finalist, HackFest Universitas Ciputra
AIRIS: edge-captured health screening with a containerised AI pipeline, built with a five-person team.
Jul – Sep 2025
AI Engineer intern, Telkom Indonesia
Took a YOLOv11 PPE-compliance system from dataset to production on Pertamina Patra Niaga’s CCTV network.
Sep 2025 – Jan 2026
S1 thesis, Universitas Brawijaya
Coordinate Attention in the YOLOv11 neck for small-object PPE detection. Final GPA 3.58 / 4.00.
Jan – Mar 2026
A booking platform with live availability and idempotent email workflows — in daily use by real customers.
Jun 2026
S3, CloudFront, Route 53, and a serverless visitor counter, deployed automatically by GitHub Actions.
Now
Moviq
Partnering with teams on AI, IoT, and web systems that have to hold up in production.
Services
One engineer from the first sketch to production — for teams that need an AI, IoT, or web system built properly and handed over cleanly.
Available for collaborationCameras that understand what they see.
Detection models trained on your own footage, wired into the cameras you already have, and shipped with the dashboard your team will actually use.
From idea to paying users.
Booking systems, dashboards, internal tools, and marketing sites — fast, accessible, and built to be maintained long after launch.
Proof: Hearth & Hair
Discuss thisDevices connected to decisions.
Edge devices, telemetry pipelines, and the cloud side that turns raw readings and frames into something people can act on.
Infrastructure that runs itself.
Cloud setup, CI/CD, data pipelines, and workflow automation that remove manual work and stay cheap to run.
Proof: Cloud Resume, Gold Tracker
Discuss thisA defined outcome, a fixed quote, and milestone demos along the way.
Best for · MVPs, pilots, and proofs of concept
A reserved block of time each month for new features, maintenance, and support.
Best for · Teams that need a technical partner on call
A focused session to review an architecture, test whether an AI or IoT idea is feasible, or plan a roadmap.
Best for · Deciding before you commit budget
A call about the problem, the constraints, and what success looks like — with honest next steps, even if that means not building it.
The riskiest assumption is tested first: a prototype on your real data, cameras, or users.
Short iterations with working demos along the way — your code, in your repository.
Deployment, monitoring, documentation, and a handover your team can run with.
Not sure which of these fits?
Describe the problem instead. You’ll get an honest answer — including when I’m not the right person for it.
Selected works
More systems I’ve designed and shipped. Keep scrolling to deal the deck.Swipe through the deck.
Now showing: Cloud Resume Challenge — AWS
This portfolio ran end-to-end on AWS: static export on S3, served via CloudFront with a custom domain on Route 53, and a serverless visitor counter on Lambda + API Gateway + DynamoDB — fully automated with a GitHub Actions deploy pipeline. The site has since moved to Vercel.
S1 thesis modifying YOLOv11 with Coordinate Attention on the neck module — improving small PPE object detection for industrial settings.
IoT health screening system integrating ESP32-CAM edge devices with a centralized AI processing unit — containerized with Docker and optimized with MLOps pipelines.
Real-time gold price monitoring with automated scraping, API integration, data storage in Google Sheets, Looker Studio visualization, and Telegram bot alerts.
This portfolio ran end-to-end on AWS: static export on S3, served via CloudFront with a custom domain on Route 53, and a serverless visitor counter on Lambda + API Gateway + DynamoDB — fully automated with a GitHub Actions deploy pipeline. The site has since moved to Vercel.
Project 1 of 4: Cloud Resume Challenge — AWS
Writing
War stories, guides, and patterns from shipping real systems — the parts that don’t fit in a case study.
Double bookings and duplicate confirmation emails are the same bug in two costumes. Patterns from building a booking platform for a real service business.
The decisions behind this site's original AWS setup — a private bucket, directory URLs at the edge, split cache headers, an atomic visitor counter — and why IAM took the most time.
Two deployments — PPE compliance on an industrial CCTV network and camera-based parking occupancy — and why the detector was the easy part.
