Skip to content
AM

LLM Engineer · Komdigi AI Talent Factory

ArkanantaMasarief

Informatics Engineering at ITS Surabaya. I build applied AI systems — fine-tuning pipelines, content-moderation models — and the backends that keep them standing in production.

Open to workSurabaya, Indonesia

I work at the seam between models and systems — the part where a promising notebook has to become something that survives real traffic, real data, and real people.

Currently an LLM Engineer at Komdigi’s AI Talent Factory, building fine-tuning pipelines and content-moderation frameworks, and a Backend Developer at Flexoo Software House.

Informatics Engineering at Institut Teknologi Sepuluh Nopember, Surabaya — GPA 3.88. Previously science track at SMA Pradita Dirgantara.

Most of what I build has an accessibility or public-interest angle: an ADHD-adaptive tutor, content safety for children, forensics tooling that other researchers can actually install.

Selected work

03 projects
01Garuda Hacks 6.0 · 30-hour buildBackend Developer

Vika AI

Real-time multi-modal AI tutor and voice agent

An adaptive learning platform for students with ADHD that teaches to the VARK learning styles — visual, auditory, read/write — instead of forcing one mode on everyone.

  • Built the Node.js, Express and MongoDB backend, and the API layer joining frontend, AI models and database.
  • Orchestrated real-time sessions that sync Gemini 2.5 Flash verbal responses with live canvas visualisation commands.
  • Shipped a live conversation engine on Google Cloud STT/TTS with custom voice-agent logic and an automated ADHD assessment flow.
TypeScriptNode.jsExpressSocket.IOMongoDBGemini 2.5 FlashDocker
02Machine Learning final projectData exploration, feature engineering, model tuning

SNBP Admission Prediction

Classification under severe class imbalance

Predicting outcomes in Indonesia's achievement-based university admission track. The real problem was not the model — it was a 90.9% class imbalance that made naive accuracy meaningless.

  • Engineered an indeks prestasi feature combining academic and non-academic achievement into one signal.
  • Demonstrated SMOTE oversampling materially outperformed random undersampling at recovering the minority class.
  • Compared LightGBM, XGBoost and Random Forest, then tuned the leader with Optuna.

Best configuration — LightGBM + logistic regression, soft voting — reached 0.735 accuracy at 0.576 ROC AUC. Honest numbers: the imbalance limits how far this data goes.

PythonLightGBMXGBoostSMOTEOptunascikit-learn
03Research tooling · recongraph, reconfsm, reconformalDevOps Engineer & Core Python Developer

Forensic Timeline

DFIR tooling, from notebooks to distribution

Three digital-forensics research tools existed as loose scripts and notebooks. I turned them into installable, documented, continuously-tested Python packages.

  • Refactored flat scripts and notebooks into modular packages managed through pyproject.toml.
  • Built GitHub Actions workflows for matrix CI and automated release to PyPI on tag.
  • Automated documentation builds via Read the Docs, and secured publishing with PyPI Trusted Publishers (OIDC) instead of long-lived tokens.
PythonGitHub ActionsPyPI OIDCRead the Docs

Experience

Jan 2026 — Present

Komdigi — AI Talent Factory

LLM Engineer

Fine-tuning pipelines for Qwen and Ministral covering image categorisation and captioning; end-to-end lifecycle of a 30,000+ image dataset; age-rating frameworks and statistical benchmarks for automated content moderation.

Dec 2025 — Present

Flexoo Software House

Backend Developer

Server-side logic and core database workflows — data validation, secure transaction flows, endpoint performance — built as modular, tested components inside an agile team.

Feb 2024 — Nov 2024

Schematics NPC

Problem Setter

Authored algorithmic problems for a national programming contest, with the test cases and reference solutions to keep the difficulty curve and the results honest.

Education

Institut Teknologi Sepuluh Nopember

Informatics Engineering, B.Sc. · Jul 2023 — Present · GPA 3.88

Credentials

  • Rekayasa Aplikasi LLM Terapan — Pusat Pengembangan Talenta Digital
  • Mastery in Deep Learning — Pusat Pengembangan Talenta Digital
  • Cloud Security Foundations — AWS Academy
  • Cybersecurity & Security Operations Foundations — Palo Alto Networks

Building something that has to actually work?