Hello World!
Syahrul here

Hands-on · · from Indonesia

I build across AI, telecommunications, and the web, from edge deployed computer vision to RF network analysis and full stack apps. This is where I show what I've made.

Explore Projects Resume

PythonPyTorchTensorFlowHugging FaceTensorRTOpenCVWeights & BiasesRoboflowMySQLGitUbuntuVue.jsJavaScriptArduino

Experience

Feb 2026 — Jun 2026
Coding Camp powered by DBS Foundation
AI Engineer — Cohort Participant (Remote)
- Completed an intensive AI Engineer learning path covering machine learning, deep learning, computer vision, and NLP, culminating in a deployed team capstone.
- Led a 6-person capstone team to design, build, and deploy Seribu Cerita, a web-based mental health support application — shipped end-to-end from concept to live product.
- Developed and deployed an IndoBERT-based emotion classification model achieving 86% accuracy on Indonesian text.
- Applied LLM APIs (Claude / GPT) to generate user-facing explanations and summaries, and presented the project as a competition pitch entry.
Jan 2025 — Jun 2025
PT Nexwave (Huawei Project)
RF & Network Optimization Intern — Semarang
- Ran drive test operations with Huawei PHU and G-NetTrack Pro, collecting KPI data (RSRP, RSRQ, SINR, throughput) across 2G/3G/4G networks for coverage and service-quality evaluation.
- Analyzed drive test logs in Genex Assistant to pinpoint weak coverage, call drops, interference, and handover failures, turning noisy field data into actionable Radio Network Optimization (RNO) recommendations.
- Conducted site surveys and supported BTS installation and commissioning — hardware setup, cabling, parameter configuration, and alarm setup for fault monitoring.
- Plotted sites and integrated EngPAR and GCell data in MapInfo, and prepared technical documentation: Excel KPI reports, AutoCAD SID drawings, and review decks.
- Authored a cellular network performance evaluation report for Site Tembarak (L900 / L1800 / L2100), covering multi-band coverage analysis and optimization recommendations.

Projects

Real-Time Road Damage Detection on Edge Devices

Real-time road damage detection from a moving vehicle, optimized for edge devices. YOLO11m compressed with mixed precision quantization (INT8 + FP16, TensorRT): 1.92–2.97× faster inference and ~65% smaller model while staying within ~1% of FP32 accuracy. Includes a live dashboard with GPS-tagged detections, map view, and damage-area estimation.

PythonPyTorchYOLO11TensorRTNVIDIA Jetson

Website

Seribu Cerita

Web-based mental health support application built as a Coding Camp 2026 capstone. Led a 6-person team from concept to deployed product; developed and deployed an IndoBERT-based emotion classification model reaching 86% accuracy on Indonesian text, handling the full ML workflow from preprocessing to integration.

PythonIndoBERTTransformersNLP

Website Source Code

Blogs

Hello, Syahrul here

Why I built this portfolio, and what I plan to document here going forward.

July 21, 2026

Hello World!Syahrul here