I began my career as a Project Control Engineer at a globally recognized EPC company, managing cost and schedules for large-scale infrastructure projects. Over time, I became deeply intrigued by the power of data and AI-driven systems, especially their potential to bring scalable solutions to the real world.
Now, I’m combining the structured mindset of engineering execution with hands-on machine learning development, from training deep learning models to deploying full-stack AI applications.
-
🐾 PawMatchAI
A hybrid model for dog breed classification and recommendation, combining CNN, Transformer, and custom feature extractors.
Designed to help users identify breeds, compare characteristics, and find a good match.
Previously featured on Hugging Face’s “Spaces of the Week”, with 30K+ visits.
→ 🌐 Try the Demo | 🗂️ Explore the Project -
🛰️ Vision Scout An advanced multi-modal scene understanding system that orchestrates YOLOv8, CLIP, Places365, and Llama 3.2 in intelligent collaboration to deliver comprehensive visual analysis. This integration enables the system to simultaneously process object detection, semantic context, environmental classification, and linguistic refinement, producing narrative descriptions that transform raw visual data into human-readable stories. The system identifies functional zones, analyzes lighting conditions, and infers activities and safety considerations through sophisticated multi-model fusion techniques. Featured in Hugging Face's "Spaces of the Week" for its innovative storytelling-driven approach to computer vision. →🌐 Try the Demo | 🗂️ Explore the Project
-
📘 Learning Record
My central repository documenting my full learning journey — from data science projects and SQL practice, to deep learning experiments and reusable helper tools. Each project includes a detailed README, reflecting both hands-on skills and structured thinking.
I write about deep learning architectures, hybrid modeling, and AI system design, blending technical clarity with conceptual depth. All articles are selected as Deep Dives.
| Title | Published | Pageviews | Engaged Views | Highlights |
|---|---|---|---|---|
| 🧠 From Fuzzy to Precise: How Morphological Feature Extractors Enhance AI Recognition | 2025/03/25 | 502 | 294 | Morphological reasoning in CNNs |
| 🧩 The Art of Hybrid Architectures: Blending Convolutional and Transformer Models for Explainability | 2025/03/28 | 1,406 | 733 | Layered hybrid design: CNN + Transformer |
| 🔗 Beyond Model Stacking: The Architecture Principles That Make Multimodal AI Systems Work | 2025/06/19 | 4,771 | 1,474 | Multimodal system design & architecture thinking |
🔹 Machine Learning & AI Enthusiast
Hands-on in computer vision, NLP, and model deployment, with a focus on building useful, explainable, and well-integrated AI solutions.
🔹 Engineer Turned Data Explorer
From managing construction schedules and cost to training models, I carry the same structured, iterative mindset — whether it’s defining MVPs or analyzing feature contributions.
I also have experience with feature engineering, data preprocessing, and traditional machine learning pipelines. I believe in the principle of "Garbage in, garbage out": a lesson that applies as much to XGBoost as it does to a poorly defined CPM schedule. A well-prepared dataset, like a well-sequenced project timeline, determines everything downstream.
I’m open to new opportunities in:
👉 AI Product / Technical PM
👉 Machine Learning Engineer
👉 Data Scientist
If you're building AI products with real world impact, I’d love to collaborate.
"Every challenge is a puzzle — it's just waiting for the right combination of algorithms and insight."
