open to collaboration

›_ hello, world. I'm

Bagus Purnama

Software Engineer who builds
full-stack products

I build full-stack products end to end — from the database schema to the last pixel — and keep exploring what's next in deep learning and AI.

~/bagus — zsh

› ~

0+

Products shipped

0

Peer-reviewed papers

0

Core technologies

∞

Curiosity for new tech

01 / About

Engineer by trade, explorer by habit.

I'm a software engineer who builds products for real businesses — ERP systems, inventory and order management, point-of-sale apps, learning platforms and company websites.

My comfort zone spans the whole stack: Spring Boot and Laravel on the back end, React, Angular, Next.js and Nuxt on the front, relational databases underneath and Docker to ship it all.

Alongside client work I keep a research habit. I've published papers on stance detection, multi-label text classification and fuzzy classifiers — and I'm always tinkering with whatever is new in deep learning and AI.

Full-stack ownership

I like owning a product end to end: the data model, the API, the interface and the details in between.

Ship it in containers

Everything I build is Dockerized and deployable the same way every time — no "works on my machine".

Always exploring

New frameworks, new paradigms, new models. I learn by building, then keep what earns its place.

02 / Tech stack

The tools I reach for.

A stack shaped by shipping real products — each tool is here because it solved a real problem.

ReactAngularNext.jsNuxt.jsSpring BootLaravelNode.jsJavaKotlinPythonTypeScriptMySQLPostgreSQLFirebaseDockerPortainer

Frontend

04

Interfaces that feel fast and stay maintainable.

  • React

    Component-driven UIs and dashboards — my default for interactive front-ends.

  • Angular

    Structured, enterprise-scale apps with TypeScript and RxJS.

  • Next.js

    Full-stack React with server rendering. This site runs on it.

  • Nuxt.js

    Vue-powered sites and company profiles with great SEO out of the box.

Backend

03

APIs and business logic for real operations.

  • Spring Boot

    Robust REST services on the JVM for inventory and enterprise systems.

  • Laravel

    Batteries-included PHP backends behind my ERP, POS and CMS projects.

  • Node.js

    Lightweight APIs, real-time services and developer tooling.

Languages

04

Typed where it matters, expressive where it helps.

  • Java

    The strongly typed backbone of my Spring Boot services.

  • Kotlin

    Concise, null-safe JVM code for services and Android.

  • Python

    My go-to for data, machine learning and research experiments.

  • TypeScript

    Type-safe JavaScript across my React, Next.js and Node.js codebases.

Databases

03

Data modelled with care — relational and realtime.

  • MySQL

    The workhorse behind most of my production apps.

  • PostgreSQL

    Advanced SQL, JSONB and extensions when the data gets complex.

  • Firebase

    Realtime data, auth and hosting for fast-moving PWAs like Bay Golf.

DevOps

02

Ship it the same way every time.

  • Docker

    Every project ships in containers — reproducible from laptop to production.

  • Portainer

    Managing containers and stacks on my servers through a clean UI.

03 / Currently exploring

Deep learning & AI.

Where my curiosity lives. My research roots are in NLP and machine learning; today I'm exploring how large language models and AI agents can make real products smarter.

Interests

Deep Learning
Natural Language Processing
Large Language Models
AI Agents
Computer Vision

Toolbox

Python
PyTorch
TensorFlow
Hugging Face
Jupyter
scikit-learn

04 / Selected work

Products I've built.

ERP, inventory, reservations and education platforms — built for real businesses and real users.

05 / Research

Published research.

Machine learning and NLP papers from my academic work — stance detection, text classification and beyond.

01

A Stance Dataset with Aspect-based Sentiment Information from Indonesian COVID-19 Vaccination-related Tweets

Data in Brief (Q2)

  • Dataset
  • NLP
  • Sentiment Analysis
Feb 2023
02

Stance Detection on Tweets with Multi-task Aspect-based Sentiment: A Case Study of COVID-19 Vaccination

International Journal of Intelligent Engineering and Systems (Q3)

  • Deep Learning
  • BiGRU-BERT
  • Multi-task Learning
Jun 2022
03

Ensemble-based Methods for Multi-label Classification on Biomedical Question-Answer Data

Journal of Information Systems Engineering and Business Intelligence (Sinta 2)

  • NLP
  • Ensemble Learning
  • BERT
Apr 2022

06 / Contact

Have an idea?
Let's build it.

Whether it's a product, a collaboration or a conversation about AI — my inbox is open.