I specialized in seamless Odoo Migrations and ERP POS optimizations for retail and industrial clients. My work focused on refactoring custom modules and transforming database schemas to ensure zero-downtime version upgrades. I architected unified Point of Sale (POS) ecosystems that synchronize real-time inventory, accounting, and CRM data across multi-branch operations. To add a layer of intelligence, I integrated AI Agents within the Odoo workflow to automate routine document handling and provide predictive insights, such as automated sales forecasting directly from POS transaction history.
1
28
I engineered a high-precision forecasting system using an ensemble approach with LSTM, ARIMA, and XGBoost to predict pharmaceutical sales trends. By performing rigorous hyperparameter tuning via GridSearchCV, I achieved a 93% prediction accuracy on historical datasets. To ensure business stakeholders could trust the results, I integrated SHAP values for model interpretability and deployed the solution as a scalable Flask API.
0
19
I developed an industrial Computer Vision system to automate the reading of tiny digits on utility meters using YOLOv8 and SAHI. To handle challenging industrial lighting, I applied advanced image preprocessing (deblurring and contrast enhancement), which improved detection reliability by 20%. The system achieved a 15% latency reduction and was deployed as an interactive Streamlit and FastAPI application for real-time use.
0
26
As a Computer Vision Engineer, I developed an end-to-end monitoring system using YOLOv7 and OpenCV for smart city infrastructure. I optimized the pipeline for resource-constrained edge devices, achieving a high-performance throughput of 25 FPS at 85% accuracy. To ensure production reliability, I implemented custom NMS (Non-Maximum Suppression) and used MLflow for rigorous experiment tracking and model versioning. The final system provides scalable, low-latency vehicle detection and license plate recognition for real-time traffic analysis.