I’m a multilingual linguist transitioning into Data Science & NLP.
With a background in education, communication, and text analysis, I bring human-centered thinking into machine learning and data work. I’m especially interested in corpus curation, NLP, ethical AI, and accessibility through language technologies.

I’m currently training in Data Science & AI at WBS Coding School (Germany) while building portfolio projects in Python, SQL, and Linguistic Data.

• 🐍 Python
• 📊 SQL
• ☕ Java (foundational)

• Data Cleaning, EDA & Feature Engineering
• Statistical Analysis & Experiment Design (basics)
• NLP Fundamentals: text preprocessing, tokenization, labeling
• Corpus Review & Linguistic Data Annotation
• Model Evaluation & Error Analysis (introductory)

• Data & ML: Pandas, NumPy, Scikit-learn
• Visualization: Matplotlib, Seaborn, Tableau, Looker Studio
• Web & Data Access: Requests, BeautifulSoup, SQLAlchemy
• Backend: Django (basics)
• NLP: Hugging Face ecosystem (introductory)

• Google Cloud Platform (basics)
• Microsoft Azure (Basics)
• Git & GitHub (collaboration, forks, PRs)
• Conda, Jupyter Notebook
• VS Code, Eclipse

• Relational Databases (SQL)
• NoSQL: MongoDB (basic)

• Structured thinking & analytical reasoning
• Clear communication of complex concepts
• Attention to detail (language, annotation, evaluation)
• User-centered and inclusive perspective

• Windows, macOS

• TCP/IP (Introduction)

• Team collaboration
• Empathy & clear communication
• Analytical & structured thinking
• Problem solving
• Initiative & self-learning

A user-friendly book lending system designed to track borrowed books, return dates, and overdue items.
Focus on practical problem-solving, data modeling, and user-oriented design.

Basic online banking tool featuring user registration, account management and transfers. Focus on Python fundamentals, data structures, and clean code practices.

Data analysis of a Brazilian e-commerce dataset, including logistics evaluation, revenue insights, operational reliability, and product value performance using SQL.

--

Production-ready template for structuring Generative AI projects.
Used to study scalable project architecture, prompt workflows, and best practices for GenAI development.

Visual analysis and diagnostic tools for machine learning model selection.
Exploring model evaluation, performance visualization, and interpretability techniques.

Machine learning pipeline for detecting fake news.
Used to explore text preprocessing, feature extraction, and supervised learning for NLP tasks.

• 🔤 Corpus Review Contributions
  Reviewing and correcting linguistic dataset entries, focusing on metadata quality and consistency
  🔗 Mozilla Common Voice

• 🇧🇷 Portuguese – Native
• 🇬🇧 English – C1
• 🇩🇪 German – B2
• 🇪🇸 Spanish – C1

🎯 My goal is to help build responsible and inclusive language technologies that empower people through data and AI.