07/16/2026 updated
100 % available
Data Scientist & Machine Learning Engineer
Padova, Italy
Worldwide
Master's Degree in Physics of Data (in progress), University of PaduaData AnalysisData MiningMachine LearningNatural Language ProcessingData ScienceDeep LearningMachine Learning Operations
Machine Learning & Deep Learning
Expertise in developing and evaluating machine learning and deep learning models using frameworks such as PyTorch, TensorFlow, and Scikit-learn, applied to tasks including fraud detection, text classification, and sentiment analysis.
Natural Language Processing (NLP)
Proficiency in NLP pipelines for text classification, sentiment extraction, and information retrieval, including implementation of Retrieval-Augmented Generation (RAG) systems and transformer-based architectures.
Data Analysis & Statistical Modeling
Strong foundation in statistical methods, probability, and optimization, with hands-on experience processing and analyzing large-scale structured datasets using Python and SQL to generate actionable insights.
Computer Vision
Experience building computer vision systems integrating LLM workflows for character recognition and large-scale document comparison.
Programming Languages
Proficiency in Python, C++, SQL, R, and Bash for data processing, modeling, and automation tasks.
Mathematics & Monte Carlo Methods
Solid background in mathematics including statistics, probability, optimization, and Monte Carlo simulation methods applied to real-world problems.
Data Engineering & Pipelines
Experience building data pipelines for cleaning, transformation, and reporting, as well as automated data collection pipelines from multiple web sources.
Tools & Development Environment
Familiarity with Git, Linux, Jupyter Notebooks, and LaTeX for version control, development, and documentation.
Generative AI & RAG Systems
Knowledge and practical experience with Retrieval-Augmented Generation (RAG) systems and generative AI methods, including contributions to the TREC-RAG 2024 initiative.
Expertise in developing and evaluating machine learning and deep learning models using frameworks such as PyTorch, TensorFlow, and Scikit-learn, applied to tasks including fraud detection, text classification, and sentiment analysis.
Natural Language Processing (NLP)
Proficiency in NLP pipelines for text classification, sentiment extraction, and information retrieval, including implementation of Retrieval-Augmented Generation (RAG) systems and transformer-based architectures.
Data Analysis & Statistical Modeling
Strong foundation in statistical methods, probability, and optimization, with hands-on experience processing and analyzing large-scale structured datasets using Python and SQL to generate actionable insights.
Computer Vision
Experience building computer vision systems integrating LLM workflows for character recognition and large-scale document comparison.
Programming Languages
Proficiency in Python, C++, SQL, R, and Bash for data processing, modeling, and automation tasks.
Mathematics & Monte Carlo Methods
Solid background in mathematics including statistics, probability, optimization, and Monte Carlo simulation methods applied to real-world problems.
Data Engineering & Pipelines
Experience building data pipelines for cleaning, transformation, and reporting, as well as automated data collection pipelines from multiple web sources.
Tools & Development Environment
Familiarity with Git, Linux, Jupyter Notebooks, and LaTeX for version control, development, and documentation.
Generative AI & RAG Systems
Knowledge and practical experience with Retrieval-Augmented Generation (RAG) systems and generative AI methods, including contributions to the TREC-RAG 2024 initiative.
Experience
Professional experience0 - 5 years
Freelancer since2026
Languages
EnglishFluentItalianGoodSpanishNative speaker
Project history
Developed deep learning models to infer public perception from text data. Applied NLP pipelines for classification and sentiment extraction.
Built automated data collection pipelines from multiple web sources. Structured datasets for downstream analytics and trend analysis.
Developed and evaluated fraud detection models using supervised learning and Monte Carlo simulation methods. Built computer vision systems implementing workflow with LLM for character recognition and large-scale document comparison. Analyzed structured datasets to support evidence based operational decisions.