initializing...
Hero

Applied AI engineer
based in Palembang, Indonesia.

APPLIED

AI ENGINEER

& DATA CODE

Detection systems, risk models,
and operational tools.

Backend AI Engineer Internship at FlyRank AI ◆ Machine Learning Engineer Internship at Telkomsel ◆ Business Intelligence Analyst Internship at Perum BULOG ◆ Runner-up Best Hacker of 10th IndonesiaNEXT by Telkomsel ◆ Apple Developer Academy 2027 @ IL ◆ Created BASA with over 7K PyPI Download ◆ Peer Reviewer at JSI: Jurnal Sistem Informasi ◆ 9 Certifications ◆
LOCAL TIME --:--
ENGINEER Muanai

Work

Selected Projects

Background

Experience

Backend AI Engineer

FlyRank AI · Internship
Jul 2026 - Present · 3 mos
Chicago, Illinois, United States · Remote
Python AI Backend

Creator and Maintainer

BASA · Open Source
Jun 2026 - Present · 4 mos

Built and maintained BASA (pip install basa), a lightweight NLP toolkit designed to make Indonesian and regional language text processing more accessible for developers, researchers, and AI practitioners.

Designed practical preprocessing workflows tailored for modern NLP applications, including text normalization, slang translation, and tokenization optimized for LLM and retrieval-based systems (RAG).

Achieved 7K+ downloads on PyPI and maintained strong open-source quality signals, receiving a perfect 100/100 score across security, vulnerability, quality, maintenance, and license checks on Socket.dev's supply chain analysis.

Python NLP Text Processing LLM Open Source PyPI Package Maintenance Data Preprocessing

Hacker

10th IndonesiaNEXT by Telkomsel · Apprenticeship
Jun 2026 - Sep 2026 · 4 mos

Awarded Runner Up – Best Hacker at the 10th IndonesiaNEXT by Telkomsel, developing Calmora, a mobile mental wellness application combining guided breathing, journaling, grounding exercises, daily micro-missions, calming sounds, and an AI conversational companion.

Built Calmora's AI companion using Retrieval-Augmented Generation (RAG) with a curated knowledge base drawing from trusted sources including WHO and CCI materials. The system achieved an LLM-as-a-Judge evaluation score of 0.93 with an average time-to-first-token of 1.93s.

Designed data protection for sensitive user data, including chat logs, using AES encryption, and collaborated with the Hipster to evaluate usability, achieving a SUS score of 76.92.

Worked with the Hustler to develop Calmora's business model and market sizing, targeting a SOM of 8,200 MAU with an estimated CAC of ~Rp500/user.

Generative AI RAG Evals Scrum Data Security React Expo

BI Analyst at Commercial Business Division

Perum BULOG · Internship
Juli 2026 – August 2026 · 2 mos
Sumsel & Babel Region · On-site

Developed ReCouncil, a desktop reconciliation tool using Python, PySide, and Pandas to match Power BI data with warehouse reports, reducing manual auditing and making anomalous warehouse transactions easier to identify and track.

Automated daily and year-to-date RKAP realization reporting across 6 business branches and 30+ commodity types using Python, generating structured Excel reports for operational monitoring.

Supported RPK selection and commodity distribution analysis by consolidating transaction and frequency data, applying SAW-based scoring and clustering to support distribution prioritization and customer grouping.

Python Pandas PySide Power BI Data Analysis KPI Reporting

ML Engineer at Business Growth & Analytics Division

Telkomsel · Internship
Dec 2025 – Feb 2026 · 3 mos
Sumbagsel Region · On-site

Engineered an end-to-end YOLOv8 object detection pipeline to automate the identification of competitor fixed broadband infrastructure from street-level imagery, replacing costly manual field surveys.

Improved overall model accuracy from 0.522 to 0.763 mAP50 (+24%) through a data-centric approach: stratified dataset splitting, physics-aware augmentation, and high-resolution training at 1248px.

Resurrected failing minority classes from near-zero (~0%) to ~50% mAP50 via targeted synthetic data injection with a strict zero-contamination validation policy.

Built a geo-spatial inference engine integrating EXIF GPS extraction and offline reverse geocoding via BPS shapefiles, transforming raw detections into regional infrastructure intelligence reports.

Python YOLOv8 OpenCV GeoPandas CVAT NumPy Shapefile / BPS EXIF Extraction

Credentials

Certifications

Huawei Certified ICT Associate — AI Training

Huawei Technologies

Issued April 2025

Deep Learning Foundation Models ML Basics AI Dev Frameworks MindSpore Applied AI
Credential ID HUC25OAITHOEO001000170
View Certificate

Generative AI Job Simulation

Boston Consulting Group X

Issued March 2026

Generative AI AI Development NLP Data Extraction Financial Analysis Data Science
Credential ID 7wn7WE2L2WuWycNc5
View Certificate

Software Engineering Job Simulation

JPMorgan Chase & Co.

Issued July 2026

Spring Framework Message Queuing REST API Java Programming Maven SQL Database Kafka
Credential ID STEpyKpKzYYmhEv5a
View Certificate

Agile Scrum Certification

MindMagine

Issued June 2026

Agile Methodology Scrum Framework Project Management Sprint Planning Team Collaboration Incremental Delivery Stakeholder Communication
Credential ID 0PhHrJiFw
View Certificate
Learning Paths

DBS Foundation x Dicoding

Coding Camp Gen AI Path · 4 certs

Belajar Dasar AI

AI Fundamentals ML Concepts DL Implementation
Dec 2025

Prompt Engineering untuk Software Developer

Prompt Engineering LLM Applications
2024

Memulai Pemrograman dengan Python

Python OOP Unit Testing Popular Libraries
Mar 2026

Machine Learning untuk Pemula

Machine Learning Scikit-learn Feature Engineering
Mar 2026
View All Certificates (PDF)

Digital Talent Scholarship

Artificial Intelligence Path · 2 certs

Associate Data Scientist + Python

Python Pandas scikit-learn
Mar 2026

Data Scientist Supervisor

Predictive Modeling Model Evaluation Data Analysis
Mar 2026

Fundamental of Microsoft Fabric & Azure

Microsoft Azure Microsoft Fabric
Mar 2026
View All Certificates (PDF)

Capabilities

Technical Stack

Languages & Data Tools
Python Java Go SQL Typescript Bash / Shell NumPy Pandas OpenCV
ML Engineering
PyTorch TensorFlow / Keras XGBoost Scikit-learn SHAP Hugging Face Numba (JIT) Computer Vision NLP RAG
Tools & Workflow
Git / GitHub Docker FastAPI pytest Streamlit Ollame uv CVAT QGIS PyQt ruff Redis

Behind the work

About

Muanai Khalifah Revindo

Curious about data,
pragmatic about impact.

Undergraduate in Informatics Engineering at Universitas Sriwijaya, building ML systems at the intersection of technical rigor and real business problems. No grand origin story, just someone who found early on that playing with data and seeing what it reveals is genuinely fun, and then realized the interesting problems live where complexity demands explainability.

These days, I'm focused on risk intelligence and operational analytics for emerging markets, work that spans credit scoring pipelines, geospatial infrastructure mapping, and production systems that survive contact with the real world. Recent projects share the same DNA: making sense of messy data in contexts where decisions matter.

The pattern-recognition habit started with stock markets at 17, still a stock investor, still thinking probabilistically about risk. That lens shaped how I approach ML: explainability by design, not afterthought. Because when regulators ask why a loan was denied, or field teams need to act on infrastructure intelligence, a black-box model becomes a liability in regulated and operational settings.

Outside of data, I draw and care about UI/UX because the best analysis means nothing if it's trapped in unusable interfaces.

Education

Teknik Informatika — Universitas Sriwijaya GPA: 3.81/4.00

Currently focused on

Risk Intelligence — credit risk, behavioral signals, explainable decisions
Operational Analytics — geospatial & computer vision for infrastructure intelligence

Organisation

Head of Academic Dept. — NAC Unsri Nov 2025 – Present
Head of Event Organizer Dept. — FASCO Unsri Dec 2024 – Dec 2025

Outside the terminal

Drawing, UI/UX design — visual thinking as a side practice
Stock investor since 17 — the original pattern-recognition habit

Muanai Khalifah Revindo

Curious about data,
pragmatic about impact.

Undergraduate in Informatics Engineering at Universitas Sriwijaya, building ML systems at the intersection of technical rigor and real business problems. No grand origin story, just someone who found early on that playing with data and seeing what it reveals is genuinely fun, and then realized the interesting problems live where complexity demands explainability.

These days, I'm focused on risk intelligence and operational analytics for emerging markets, work that spans credit scoring pipelines, geospatial infrastructure mapping, and production systems that survive contact with the real world. Recent projects share the same DNA: making sense of messy data in contexts where decisions matter.

The pattern-recognition habit started with stock markets at 17, still a stock investor, still thinking probabilistically about risk. That lens shaped how I approach ML: explainability by design, not afterthought. Because when regulators ask why a loan was denied, or field teams need to act on infrastructure intelligence, a black-box model becomes a liability in regulated and operational settings.

Outside of data, I draw and care about UI/UX because the best analysis means nothing if it's trapped in unusable interfaces.

Education

Teknik Informatika — Universitas SriwijayaGPA: 3.81/4.00

Currently focused on

Risk Intelligence — credit risk, behavioral signals, explainable decisions
Operational Analytics — geospatial & computer vision for infrastructure intelligence

Organisation

Head of Academic Dept. — NAC Unsri Nov 2025 – Present
Head of Event Organizer Dept. — FASCO Unsri Dec 2024 – Dec 2025

Outside the terminal

Drawing, UI/UX design — visual thinking as a side practice
Stock investor since 17 — the original pattern-recognition habit