I hold a PhD in Biotechnology and currently work at Alura, where I develop and teach courses on data analysis, artificial intelligence, and machine learning, empowering professionals to extract value from data and build intelligent systems.
Throughout my career, I have worked on a variety of topics, including:
🔹 Machine Learning and Predictive Modeling – Development of predictive models, algorithm optimization, time series forecasting, and neural networks.
🔹 Artificial Intelligence and Generative Models – Sentiment analysis, information extraction from documents, chatbot development using Retrieval-Augmented Generation (RAG), and creation of data-driven applications.
🔹 Data Analysis and Visualization – Data manipulation and structuring, large-scale data processing, statistical modeling, and data visualization.
Currently, my focus is on developing AI-driven solutions, especially in autonomous agents and generative models. I aim to explore how these technologies can be strategically applied to solve complex problems and automate processes.
-
Programming Languages: Python, R, SQL
-
Data Analysis & Visualization: Pandas, NumPy, dplyr, ggplot2, tidyr, Matplotlib, Seaborn, Plotly, Power BI, Looker Studio
-
Statistical Modeling: Statsmodels, Prophet
-
Machine Learning & Deep Learning: Scikit-learn, XGBoost, NLTK, TensorFlow
-
Generative AI & LLMs: LangChain, LlamaIndex, Langflow, Hugging Face Transformers
-
Notebooks & Platforms: Jupyter Notebook, Databricks, Google Cloud Platform
-
Big Data & Cloud: Apache Spark, Google BigQuery
Courses - Alura 👩🏫
- LlamaIndex: criando um chatbot com a técnica RAG
- LlamaIndex: analisando dados com Pandas
- Hugging Face: explorando e aplicando soluções com modelos de IA
- Estatísticas com R: testando modelos de regressão
- Regressão: aprimorando os resultados com XGBoost
- Regressão: prevendo séries temporais com Prophet
- Data Science: analisando e prevendo séries temporais
- TensorFlow: implementando um perceptron de múltiplas camadas (MLP)
- Classificação: melhorando o desempenho com XGBoost
- Classificação: resolvendo problemas multiclasse
- Power BI: criando relatórios com auxílio de IA
- Machine Learning: utilizando ChatGPT como assistente
- ChatGPT: otimizando a qualidade dos resultados
- Data Visualization: criando gráficos com bibliotecas Python
- Pandas I/O: trabalhando com diferentes formatos de arquivos
-
Data Heroines - Saving the World Through Data (Kaggle Competition with Carolina Dias and Marivaldo Torres Junior)
-
Machine Learning in Healthcare: Predicting the Need for Hospitalization in ICU Beds During the COVID-19 Pandemic (in portuguese)
-
Data Analysis: National Immunization Program (in portuguese)
-
Analysis of Hospital Costs of SUS (Unified Health System) and Evolution of Mortality Rates in Brazil (in portuguese)
-
Drug Discovery: Direct Search for New Drugs Using Specific Molecular Targets and Their Mechanisms of Action (MoA) (in portuguese) - 🏆 this project was selected as one of the 10 highlights, among more than 200 projects, in the 2021 Alura Data Immersion.
- Quais os efeitos do Storytelling no nosso corpo?
- Time Series Forecasting: Prophet é mesmo um Profeta?
- Como migrar para Tecnologia?
-
Fungal Dysbiosis Correlates with the Development of Tumor-Induced Cachexia in Mice
-
Draft Genome Sequence of 11399, a Transformable Citrus-Pathogenic Strain of Xylella fastidiosa
-
Comparative Genomic Analysis of Coffee-Infecting Xylella fastidiosa Strains Isolated from Brazil
-
Genomic Sequencing of Two Coffee-Infecting Strains of Xylella fastidiosa Isolated from Brazil
