For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

LoginCreate account
Invite to Job
Gilang Heavy

Gilang Heavy

Backend Engineer | RLHF & Code Generation Review

INDONESIA flag
Semarang, Indonesia
$25.00/hrIntermediateScale AI

Key Skills

Software

Scale AIScale AI

Top Subject Matter

Software Engineering - Backend Engineer
Healthcare - Medical Record & Patient Data

Top Data Types

TextText
DocumentDocument

Top Task Types

Red Teaming
Bounding Box
Classification
Transcription
Evaluation Rating

Freelancer Overview

As a Senior Software Engineer with over 8 years of experience, my core expertise lies in Backend Architecture, Node.js, JavaScript, API development, and SQL databases. My extensive background in building scalable systems and conducting rigorous code reviews translates perfectly into the AI Training space, specifically for evaluating and debugging AI-generated code. Recently, I have applied these analytical skills to Reinforcement Learning from Human Feedback (RLHF) and AI model evaluation. I specialize in Technical Logic Evaluation, Code Generation Review, and algorithmic optimization, ensuring that AI outputs are accurate, efficient, and production-ready. Education includes a Bachelor of Science, Stikubank University (2020).

IntermediateEnglishIndonesianJavanese

Labeling Experience

Audio Transcription & Localization

AudioTranscription
Contributed to native-level Indonesian audio transcription and localization projects. Ensured that linguistic nuances, cultural context, and dialectal accuracies were correctly captured to train high-fidelity audio models.

Contributed to native-level Indonesian audio transcription and localization projects. Ensured that linguistic nuances, cultural context, and dialectal accuracies were correctly captured to train high-fidelity audio models.

2026 - Present

RLHF & Foundational Model Evaluation

ImageRed Teaming
Participated in breaking ground models and baseline testing. Assessed AI responses for logical reasoning, factual accuracy, constraint adherence, and potential edge cases.

Participated in breaking ground models and baseline testing. Assessed AI responses for logical reasoning, factual accuracy, constraint adherence, and potential edge cases.

2026 - 2026

Code Review

Computer Code ProgrammingEvaluation Rating
Acted as a human-in-the-loop (HITL) evaluator to verify AI-generated code. Tasks included debugging complex Node.js/JavaScript & PHP scripts, evaluating algorithm efficiency, and rewriting code to meet strict production standards.

Acted as a human-in-the-loop (HITL) evaluator to verify AI-generated code. Tasks included debugging complex Node.js/JavaScript & PHP scripts, evaluating algorithm efficiency, and rewriting code to meet strict production standards.

2025 - 2026

Education

S

Stikubank University

Bachelor of Science, Information Technology (Computer Science)

Bachelor of Science
2016 - 2020

Work History

D

Dicoding Indonesia

Code Reviewer

Bandung
2026 - Present
M

Ministry of Health of the Republic of Indonesia

Software Engineer

Semarang
2021 - Present