Transforming Big Data into Strategic Intelligence: Specialist in Computer Vision, Data Engineering, and MLOps.
Data Scientist focused on scalable architectures and high-complexity systems. My expertise lies at the intersection of statistical rigor (Time Series) and the forefront of Artificial Intelligence (Deep Learning & Computer Vision). In 2026, my focus is on creating AI solutions that not only predict but optimize entire business ecosystems.
| Category | Dominant Technologies |
|---|---|
| Data Engineering | Spark, Hadoop, Apache HBase, ETL Pipelines (Parquet/DataLakes) |
| Deep Learning | TensorFlow, Keras, YOLOv8/v10, LSTM, Transformers |
| MLOps & DevOps | Docker, Podman, DVC (Data Version Control), Kubernetes |
| Analysis & Math | Python, R, SQL, ANOVA Tests, Bayesian Inference |
| Cloud | Azure Machine Learning, AWS SageMaker |
Intelligent inventory and purchasing optimization with computer vision.
- Differential: Real-time shelf monitoring via YOLO + OpenCV integrated with demand forecasting and purchase recommendation modules.
- Stack: Python, Pandas/NumPy, Scikit-learn, LightGBM, Prophet, Streamlit, Docker, DVC.
- Impact: Reduction of costs, mitigation of stockouts, and improved liquidity through leaner inventory management.
High-fidelity synthetic data engine for inventory optimization.
- Differential: Integration of real exogenous climate variables (INMET) via API for complex seasonality modeling.
- Stack: LSTM vs. Prophet, advanced Feature Engineering, DVC.
- Impact: Theoretical reduction of stockout in simulation models.
AI-assisted early detection system.
- Focus: Model interpretability (SHAP/LIME) for medical decision support.
- Techniques: Convolutional Neural Networks (CNNs), Image Segmentation.
- Postgraduate in Computer Vision: Focus on high-performance architectures.
- Big Data Specialization: Hadoop ecosystem and real-time processing with Spark.
- 2026 Focus: Cloud model scalability and data sovereignty (On-premise AI).
