I build AI and machine learning systems for real-world engineering and data-driven applications, with a focus on deep learning, computer vision, intelligent infrastructure, model evaluation, and applied AI research.
My work spans the full ML workflow — from data preprocessing and model development to evaluation, explainability, optimization, and deployment-oriented workflows.
- 🎓 Computer Science graduate
- 🤖 Focused on Artificial Intelligence & Machine Learning
- 🧠 Working with Deep Learning and Computer Vision
- 🔬 Interested in Applied AI Research & Explainable AI
- ⚙️ Building AI solutions for engineering and industrial systems
- 📊 Experienced in predictive modeling, analytics, and optimization
- 🔄 Expanding my work in MLOps, LLM Evaluation, and AI Observability
Languages
Python · SQL · C#
Machine Learning & Deep Learning
PyTorch · Scikit-learn · XGBoost · CNN · LSTM
Computer Vision & Explainable AI
OpenCV · MediaPipe · Grad-CAM · Pose Estimation
Data & Visualization
Pandas · NumPy · Matplotlib · Plotly · Power BI
Engineering & MLOps
Git · GitHub · Jupyter · Google Colab · Model Evaluation · ML Workflows
Deep Learning · Medical Imaging · PyTorch · Explainable AI
A research-oriented deep learning architecture for medical image classification using Adaptive Global Context learning.
The project combines convolutional feature extraction, multi-scale contextual modeling, adaptive feature fusion, and explainability techniques for medical image analysis.
Highlights
- Custom deep learning architecture
- Adaptive Global Context Block
- Medical image classification
- Grad-CAM explainability
- Ablation and model evaluation workflow
- PyTorch implementation
Industrial AI · Machine Learning · XGBoost · Optimization
An AI-powered analytical platform for studying water distribution networks using machine learning, predictive analytics, and optimization techniques.
Highlights
- Water network data processing
- Pressure and demand analysis
- Predictive modeling
- PRV analysis and optimization
- XGBoost-based modeling
- Particle Swarm Optimization
- Interactive visualization
Power BI · MLOps Analytics · Model Monitoring · Data Visualization
An interactive Power BI dashboard designed to analyze and visualize machine learning model performance and operational metrics.
Highlights
- Accuracy, Precision, Recall, and F1 monitoring
- Confusion matrix analysis
- Model drift indicators
- Operational alert analysis
- Model comparison
- Executive-level KPI reporting
I'm currently expanding my work in:
- LLM Evaluation & Observability
- AI Model Monitoring
- Computer Vision
- Explainable AI
- Industrial AI
- Intelligent Infrastructure
- MLOps & ML Systems
- AI for Cybersecurity
I am particularly interested in building AI systems that go beyond isolated experiments and move toward:
Reliable Models → Explainable Decisions → Reproducible Pipelines → Real-World AI Systems
- AI/ML Engineering opportunities
- Applied AI research
- Machine Learning projects
- Computer Vision projects
- Industrial AI applications
- Open-source collaboration
LinkedIn · Portfolio · Hugging Face · GitHub