Miguel Aguilar-Ortega

Developed machine learning models to optimize business processes, handling end-to-end workflows from data preparation to deployment on Azure Machine Learning. Built automation solutions using Generative AI tools like Azure AI Foundry and PromptFlow. Gained practical experience with Retrieval-Augmented Generation (RAG) to enhance language models and improve user interaction and business efficiency.

GreenMov https://green-mov.eu/

Development and deployment of ML models using Python libraries including scikit-learn, pandas, tensorflow, statsmodels, numpy, nltk, and tools like Docker, Kubernetes, MLFlow, KServe, and SQL to address mobility challenges within the context of Smart Cities. Leading technical coordination with the architecture team to integrate AI models effectively. Utilization of Smart Data Models to standardize information sharing across platforms.

SOLSTICIAhttps://www.linkedin.com/company/proyecto-solsticia?trk=p ublic_post_comment-text

Development of a monitoring system using Kubeflow, MLFlow, PostgreSQL, fastapi and evidentlyai to enhance the model lifecycle in Kubernetes environments. Development and deployment of AI models to support advanced analytics and decision-making processes, employing tools such as Kubeflow Pipelines, tensorflow, scikit-learn, MLFlow, and SQL.

Development and deployment of AI models for analyzing client surveys using Natural Language Processing techniques, with Python packages such as nltk, fastapi, scikit-learn, and pandas, achieving an 80% reduction in survey analysis time. Creation of dashboards with Qlik to summarize and visualize information, supporting data analysis. Extract, synthesize, and interpret large volumes of data hosted in relational databases, including SQL Server and MySQL.