Fullstack engineer, with a second track in data and machine learning.
Flutter, Laravel and Supabase in production. Two paid client platforms live, an internship at PT Pos Indonesia, and a thesis presented at IC2IE 2026.
Informatics graduate from Telkom University. I build web and mobile apps end to end, from the database schema to the admin dashboard, and I have shipped them for a paying client and for PT Pos Indonesia.
- EDUCATION
- S1 Informatics, Telkom University · GPA 3.76
- LOCATION
- Bekasi, Indonesia
- AVAILABILITY
- Available immediately
- LOOKING FOR
- Fullstack, data and ML roles
A job-application tracker for Indonesian job seekers, with AI that reads job posts and company emails.
Built for daily use: H-3 and H-1 reminder emails through Vercel Cron and Resend that never send twice, follow-up dates, CSV export, account deletion, and a read-only demo account that resets itself every day.
- Next.js
- React
- TypeScript
- Tailwind CSS
- shadcn/ui
- Prisma
- PostgreSQL
- Neon
- Zod
- Vitest
- Playwright
- Vercel
Flutter mobile app and Laravel web companion on one Supabase backend, synced in real time. The Android app was the priority and shipped ready for testing; the web version was a side track and was left unfinished when the internship ended.
Led labs on process management, memory, file systems and synchronization; evaluated assignments and projects.
Student grouping and liaison assignment, Convention Hall seating plan, Student Fair timetable.
Projects
9 projectsEvery project opens a page with the role, stack and outcome behind it.
Commission Tracker
ACTIVELY MAINTAINEDSole developer · Free web app for illustrators
A free web app for illustrators who take commissions. It tracks each order from waiting list to delivery, shows income and unpaid balances, and gives every client a private link to follow their order.
- Next.js
- React
- TypeScript
- Tailwind CSS
- shadcn/ui
- Supabase
- Recharts
- dnd-kit
- Zod
- Vitest
- Vercel
Portfolio Site
ACTIVELY MAINTAINEDSole developer · Personal project
This site itself: a Next.js portfolio with a Supabase-backed admin CMS, bilingual content, and a static seed fallback so it still renders with no database at all.
- Next.js
- React
- TypeScript
- Tailwind CSS
- Supabase
- Framer Motion
SUGIH
LIVEFullstack developer · Paid client, team of 2
Company profile site for SUGIH, a kretek brand under CV. Prioritas Group, with an admin panel the client uses to manage products, news and job openings. Built with one other developer.
- Laravel
- Tailwind
- Alpine.js
- GSAP
- PostgreSQL
- Vercel
QSAR Toxicity Prediction (GWO-ANN)
PRESENTED AT IC2IE 2026Researcher · Undergraduate thesis, paper accepted at IC2IE 2026
Undergraduate thesis, accepted at IC2IE 2026. A neural network tuned by the Grey Wolf Optimizer predicts whether a chemical is toxic to the estrogen receptor, on data with 18.6 non-toxic samples for every toxic one.
- Python
- TensorFlow / Keras
- Scikit-learn
- RDKit
- imbalanced-learn
- NiaPy
- Pandas
- NumPy
- Languages & frameworks
- Flutter, Dart, Laravel, PHP, Python, FastAPI, Golang, TypeScript, JavaScript, React, Next.js, Tailwind CSS, Alpine.js, REST API
- Data & machine learning
- TensorFlow / Keras, PyTorch, Scikit-learn, Pandas, NumPy, RDKit, NiaPy, OpenCV, ONNX, EasyOCR, TrOCR
- Platform & infrastructure
- Supabase, PostgreSQL, MySQL, Firebase, Docker, Nginx, Deno, Vercel, Linux, Git
- Tools & workflow
- Figma, VS Code, Android Studio, Jupyter, Vite, GSAP, Framer Motion, Swiper, Ollama, Gemini, Claude Code, Cursor, Copilot
Prediction of ER-LBD Toxicity using an ANN Optimized by Grey Wolf Optimizer
Tox21 dataset, 8,751 compounds at 18.6:1 imbalance. Morgan fingerprints and physicochemical descriptors reduced to 500 features by Mutual Information; SMOTETomek applied only inside the training split.
- F1-SCORE
- 0.5809 → 0.5946
- FALSE POSITIVES
- 37 → 22
- ARCHITECTURE
- 54-32-128
- FEATURES
- 500 via MI