Summary
Overview
Work History
Education
Skills
Websites
Timeline
Generic

BEATRICE SILVA FERNANDES

So Paulo

Summary

Highly skilled Senior Data Scientist with over 6 years of experience in the field of Data Science, specializing in Natural Language Processing (NLP) and machine learning. Possesses an MBA in Data Science and Analytics from Universidade Estadual de Campinas (UNICAMP), combining advanced statistical modeling with real-world data analysis expertise. Proficient in Python software development and experienced in the full lifecycle of machine learning projects, from data collection and preprocessing to deployment and monitoring. Adept at leveraging NLP techniques, large language models (LLMs), and machine learning frameworks to derive insights and build efficient, scalable solutions for complex business challenges.

Overview

7
7
years of professional experience

Work History

Senior Data Scientist

Vox Radar
So Paulo
01.2024 - Current
  • Lead the development and deployment of Natural Language Processing (NLP) solutions to process and interpret large-scale textual data from diverse sources
  • Extensive experience in fine-tuning and deploying state-of-the-art large language models (LLMs) such as GPT, BERT, and their open-source equivalents for various NLP tasks including text classification, summarization, and sentiment analysis
  • Spearheaded the design and implementation of Retrieval-Augmented Generation (RAG) systems, improving the accuracy and efficiency of information retrieval tasks
  • Developed machine learning pipelines for complex tasks such as clustering, classification, and recommendation, utilizing libraries like pandas, numpy, scikit-learn, pytorch, and spacy
  • Worked with advanced data collection techniques including asynchronous web scraping using Playwright, Selenium, and other Python-based libraries
  • Managed and optimized the operationalization of vectorized databases using Postgres and ElasticSearch to ensure fast and accurate data retrieval
  • Collaborated cross-functionally to ensure the delivery of robust, scalable Python-based solutions adhering to the best practices of software development

Researcher

Caeni UNICAMP
So Paulo
01.2018 - Current
  • Engaged in research at the intersection of political science and data science, applying econometric techniques, machine learning, and NLP to understand complex political systems
  • Led data science projects focusing on the relationship between mass media and political actors using NLP and computer vision methodologies
  • Published a research paper on the dynamics of Brazil's executive-legislative relations, funded by the So Paulo Research Foundation (FAPESP), utilizing web scraping and data processing techniques
  • Delivered short courses on integrating data science, NLP, and machine learning into the social sciences, helping students understand quantitative methodologies in political analysis

Data Scientist

Vox Radar
So Paulo
02.2022 - 12.2023
  • Developed and deployed machine learning models focused on NLP, leading to improvements in the automation of data analysis and decision-making
  • Conducted advanced feature engineering and statistical analysis to enhance the accuracy and performance of predictive models
  • Contributed to the creation of end-to-end data science workflows, from data ingestion and preprocessing to model training and validation

Data Scientist

Plano CDE - Pesquisa, Inovao, Impacto
So Paulo
03.2020 - 08.2020
  • Conducted data collection and analysis for socio-economic research using microdata from the Brazilian Institute of Geography and Statistics (IBGE), with a focus on social classes C, D, and E
  • Implemented data preprocessing techniques and built statistical models to derive actionable insights from large-scale datasets

Fellow in the Social Innovation Program

USP Innovation Agency
So Paulo
11.2018 - 03.2020
  • Co-founded and served as Communication Coordinator for Marabunta Brasil, managing a team of 9 volunteers in creating and disseminating content on public policy and organic food production
  • Conducted comprehensive research on the organic food supply chain, exploring public policies and market trends to drive strategic decisions for the organization

Research Fellow

FAPESP Research Fellowship
So Paulo
06.2019 - 01.2020
  • Awarded a research grant from the So Paulo Research Foundation (FAPESP) for a project analyzing Brazil's executive-legislative dynamics through data science methodologies
  • Employed web scraping, natural language processing, and econometric models to analyze legislative documents, resulting in a publication in the Brazilian Political Science Review

Education

Master of Business Administration (MBA) - Data Science and Analytics

Universidade Estadual de Campinas (UNICAMP)
05.2023

Bachelor's Degree - History

Pontifícia Universidade Católica de São Paulo (PUC-SP)
01.2020

Skills

  • Python
  • R
  • SQL
  • Pandas
  • Numpy
  • Scikit-learn
  • Statsmodels
  • Pytorch
  • Spacy
  • NLP
  • Fine-tuning large language models (LLMs)
  • Topic modeling
  • Clustering
  • Classification
  • Regression analysis
  • Web scraping (Playwright, Selenium)
  • Database design (Postgres, ElasticSearch)
  • Data transformation

Websites

Timeline

Senior Data Scientist

Vox Radar
01.2024 - Current

Data Scientist

Vox Radar
02.2022 - 12.2023

Data Scientist

Plano CDE - Pesquisa, Inovao, Impacto
03.2020 - 08.2020

Research Fellow

FAPESP Research Fellowship
06.2019 - 01.2020

Fellow in the Social Innovation Program

USP Innovation Agency
11.2018 - 03.2020

Researcher

Caeni UNICAMP
01.2018 - Current

Master of Business Administration (MBA) - Data Science and Analytics

Universidade Estadual de Campinas (UNICAMP)

Bachelor's Degree - History

Pontifícia Universidade Católica de São Paulo (PUC-SP)
BEATRICE SILVA FERNANDES