ML Engineer / Researcher
RUDI
FIRDAUS
I build computer vision systems and data infrastructure that work outside the notebook. First-author IEEE publication on vehicle detection, Vice Head of a 54-person research lab, and hands-on experience shipping AI to production — from RAG pipelines to internal tools real teams depend on.
cls:human · Bandung, Indonesia Research
Peer-reviewed & in progress
Optimizing YOLOv11 for Vehicle Detection in Low-Visibility CCTV Footage
ICSINTESA 2025 — 5th International Conference of Science and Information Technology in Smart Administration
- 0.896
- mAP@.5
- 0.678
- mAP@.5-.95
- 122
- FPS
- 8.2 ms/img
- latency
Traffic Flow Estimation under Low-Visibility Conditions
Extending the IEEE paper's object detection work to traffic flow estimation using multi-object tracking (ByteTrack) and speed measurement per Indonesian Highway Capacity Manual (PKJI) standards. Focus on low-visibility robustness from CCTV footage.
Read more →Selected work
Research, shipped to production
ScreenAI
AI recruitment screening that pairs NER-based blind screening with RAG competency scoring and Explainable AI to rank candidates fairly and transparently.
LabLink
A centralized internal system for MBC Laboratory — members, inventory, on-call rosters, attendance, and a transparent cash ledger — replacing a sprawl of scattered docs, drives, and spreadsheets.
Flood Impact Segmentation
A 10-class Swin Transformer + FPN model that maps flood impact from aerial imagery, built for the national Dolanan Data NEXUS 2026 competition — a Top-10 finalist entry.
Stack
Tools I actually use
Languages
- Python
- TypeScript
- SQL
- Bash
ML / DL
- PyTorch
- YOLO (v8/v11)
- Transformers (HuggingFace)
- scikit-learn
- OpenCV
- LangChain
- ChromaDB
MLOps & Infra
- Docker
- FastAPI
- VPS (self-hosted)
- RAG Pipelines
- PostgreSQL
- Supabase
- Git
Full-stack
- React
- Vite
- Astro
- Tailwind CSS
- shadcn/ui