Electronic Engineer | MSc. Data Science | MSc. Artificial Intelligence
Rise and rise again until lambs become lions
- Languages: Python, SQL, C, C++, C#, JavaScript
- Data Science: Machine Learning, Deep Learning, Statistics, Data Visualization
- Tools & Frameworks: Jupyter Notebook, Pandas, NumPy, Dask, Scikit-learn, TensorFlow, PyTorch, FastAPI, Docker, Airflow, MLflow, UV
- Generative AI & LLMs: Prompt Engineering, Retrieval-Augmented Generation (RAG), LLM Evaluation, LLM Application Development, AI Agents / Agentic Workflows
- MLOps & AI Engineering: Model Deployment, Model Monitoring, CI/CD for ML, Feature Engineering, Data & Model Versioning
- Other Areas: Image Processing, Computer Vision, Data Analytics, Automation, ETL
-
SARA | Sistema de Análisis mediante RAG y Agentes | Identificación inteligente de oportunidades en Secop II. Master's project implementing an intelligent agentic and RAG (Retrieval-Augmented Generation) architecture to process public procurement documents. Designed for the automated analysis and identification of bidding opportunities within the SECOP II platform.
-
End-to-end RAG for transsactional data proccesing with Airflow orquestation. End-to-end technical solution for transactional data processing, modeling in BigQuery, orchestration with Airflow and a RAG (Retrieval Augmented Generation) system.
-
Titanic Predictor API. Titanic survival prediction API with FastAPI and Docker. ML model, Swagger UI documentation, and ready for deployment.
-
Analytics Fundamentals I. Medical data analysis project focused on Polycystic Ovary Syndrome (PCOS).
-
Predicting-Patient-Charges. End-to-end MLOps project implementing machine learning pipeline to predict patient insurance charges. Built with PyCaret for automated ML, Flask web app, Docker containerization, Azure cloud deployment, and GitHub Actions CI/CD. Includes comprehensive testing, documentation, and live production environment.
Note: Explore more of my projects. You can see them all at github.com/alfa7g7?tab=repositories
- Advanced Deep Learning Architectures (e.g., Transformers, GANs)
- MLOps practices for robust model deployment and monitoring
- Reinforcement Learning applications
- Advanced LLM systems (retrieval optimization, hallucination mitigation, and evaluation frameworks)
- LLMOps in production (guardrails, observability, and prompt/version management)
- Efficient fine-tuning and inference optimization (LoRA/PEFT and serving performance)
- Responsible AI and AI Governance for enterprise-grade solutions
Thanks for visiting my profile! 🚀