Computer Science graduate specialising in computer vision and fullstack engineering - from deep learning training through to production deployment.
01. RESEARCH & ML
Computer Vision & Medical MRI
02. FULLSTACK WEB
Next.js, APIs & Edge DB
03. MOBILE APPS
React Native & Offline-First
2022 - 2026
Universitas Gunadarma
S.Kom, Informatics Engineering
GPA 3.76 / 4.00
Informatics graduate from Universitas Gunadarma, class of 2026. The thesis built a hybrid Autoencoder + CNN that sorts MRI scans into four tumour classes. Internal test accuracy reached 89.31 percent on 4,735 cleaned images. On BraTS 2020 data the model had never seen, 71.25 percent.
Most of the work happens before training. Auditing and merging three public MRI sources moved accuracy further than any architecture change did. The pattern repeated in the web and mobile projects: the unglamorous step decides the result.
The rest is delivery. Python and Flask on the server. TypeScript and React Native on the client. Turso and SQL Server in the data layer. A model in a notebook is still a hypothesis. What gets built around it decides whether anyone can trust the output.
Machine Learning
Web & Backend
Mobile
Database & Cloud
Tools
Quick Connect
Based in Jakarta, ID · UTC+7
Computer vision research to fullstack systems - built from model training through to production deployment.
Hybrid Autoencoder + CNN that sorts MRI scans into four tumour classes, reporting the external validation number next to the internal one.
A diary, rating and discovery layer for Roblox experiences, built on the official API.
Offline-first PWA for village field officers, with an admin view that watches submissions arrive.
Private single-user Android fitness tracker: local-first, no account, no backend.
Multimedia portal where the content hierarchy dictates a neo-brutalist identity.
Live sync from GitHub · 34 public repositories (@Mriskiali)
GitHub ProfileApplied research, production engineering roles, and verified industry credentials.
Thesis researcher
·Universitas Gunadarma
2025 - 2026
Built a hybrid Autoencoder + CNN for four-class brain tumour classification on 4,735 cleaned MRI images.
Ran a CLAHE ablation and a three-stage training schedule: 89.31 percent internal accuracy, 71.25 percent on BraTS 2020.
Team member: frontend and offline sync
·SPKPPSU Field Reporting App
2026 - 2026
Built the offline-first PWA for village field officers: IndexedDB queue, service worker sync, and an admin view for monitoring submissions.
Independent projects
·Self-directed
2023 - now
Built and deployed web, mobile and machine-learning projects on Vercel, Streamlit and Railway.
Institutional & verified credentials
Design Thinking Workshop
Samsung Solve for Tomorrow × Skilvul · 2025 · Concept paper score 92.1
Belajar Dasar AI
Dicoding Indonesia · 2025
Advanced Database Systems
Computer Laboratory, Universitas Gunadarma · 2025
SQL Server - Intermediate
Computer Laboratory, Universitas Gunadarma · 2025
Oracle - Intermediate
Computer Laboratory, Universitas Gunadarma · 2025
Fundamental Web Programming
Computer Laboratory, Universitas Gunadarma · 2025
JavaScript Programming Language Fundamental
Computer Laboratory, Universitas Gunadarma · 2025