AI applied to critical workflows
I have experience with audit automation, contract reading, clause extraction, regulatory compliance and technical information retrieval using LLMs and multi-agent systems.
Python
AI Engineering
NLP
MLOps
LLMOps
GenAI
Hello, welcome. I am Flávia, a Senior Data Scientist with 6 years of experience in AI, data and automation. My work combines generative AI, NLP, machine learning and the full data process behind data science, from information structure and quality to modeling, automation and real-world application.
- Experience
- 6 years in data, AI and analytics
- Positioning
- Senior Data Scientist
- Specialty
- Generative AI, RAG and data architecture
- Academic Background
- UnB, USP and IESB
Executive Summary
What I bring to data and product teams
Strong science and engineering foundation
I work with Python, Spark, Databricks, Delta Lake, MLflow, Streamlit, LangChain and pipelines designed for governance, monitoring and production.
Communication and continuous learning
Alongside professional delivery, I keep strong technical production, recent Data Engineering certifications and academic research in Data Science.
Frameworks and Technologies
Tools and ecosystems I have already worked with in practice
LangChain
Langflow
Flowise
AutoGen
Codex
Llama
Kiro
Antigravity
Azure
AWS
Databricks
Spark
Oracle
Experience
Areas where I have worked with data, automation and applied AI
Auditing and analytics at scale
Role: Senior Data Scientist
Work with PySpark, Databricks and SQL in analytical flows, data quality, inconsistency analysis, automated refresh and applied AI for operational support.
Document automation and financial flow
Role: Senior Data Scientist / Senior AI Engineer
Development of solutions for PDF reading, rule extraction, financial-flow organization and automation with agents, workflows and analytical persistence.
Document assistants with RAG and validation
Role: AI Specialist Data Scientist
Creation of LLM-based solutions for structured document extraction, retrieval, validation interfaces and pipeline evolution with observability.
Technical extraction and text classification
Role: Data Scientist / AI Specialist
Work across machine learning, NLP, information extraction, text classification, validation interfaces and the evolution from heuristic pipelines to generative AI.
Territorial analysis and analytical monitoring
Role: Data Analyst
Analysis of large datasets, indicator construction, territorial monitoring, dashboards and analytical support for operational and policy-oriented reading.
Web scraping, NLP and visualization
Role: Data Science Intern
Automated content collection, NLP with spaCy, data visualization and experimental modeling and deep learning projects.
Areas of Practice
A hybrid profile combining technical depth, real-world execution and business context
Generative AI and LLMOps
Development of solutions with LLMs, RAG, agents and structured workflows for extraction, analysis, automation and decision support in corporate contexts.
Machine Learning and NLP
Experience with classification, supervised models, natural language processing, embeddings, deep learning and applications focused on text, documents and unstructured data.
Data, Architecture and Pipelines
Design of analytics environments, scalable pipelines, governance, data quality and modern architecture supporting analytics, machine learning and AI.
Analytics and Decision Support
Exploratory analysis, dataset reconciliation, dashboards, monitoring and translation of data into clear insights for technical, operational and business teams.
Education and Certifications
Credentials that support my technical practice
UnB, USP and IESB
Master’s in Applied Computing at UnB, MBA in Artificial Intelligence and Big Data at USP, and a Bachelor’s degree in Data Science and Artificial Intelligence from IESB.
Data Science and legal texts
Data Science research line focused on named entity recognition in legal texts, supported by a strong foundation in databases, large-scale data mining and applied experimentation.
Data Engineering and Databricks
Recent certifications in Airflow, Spark, Snowflake, BigQuery, Modern Data Stack and Databricks tracks connected to machine learning data preparation and retrieval agents.
Highlighted Certifications
Certifications
Databricks
Badge connected to machine learning tracks and modern data ecosystems.
Retrieval Agents
Building retrieval agents and applied workflows inside the Databricks ecosystem.
Palantir Foundry
Training focused on building data solutions and operations on enterprise platforms.
AIP Foundations
Additional foundation in AI application and workflows within the Palantir ecosystem.
Functions, Tools and Agents with LangChain
Specialization in OpenAI Function Calling and LangChain tools for turning LLMs into operational agents.
Google Data Analytics Professional Certificate
End-to-end analytics workflow using BigQuery, R, SQL and Sheets.
Introduction to LangGraph and LangSmith
Training in graph-based orchestration, observability, traceability and evaluation of LLM applications, strengthening AI engineering practices.
Academic Experience
Read my thesis projects
NER in legal texts with spaCy and a published application
In my undergraduate capstone, I developed two spaCy models fine-tuned for named entity recognition in Brazilian legal texts using the LeNER-Br dataset and published a working app on Hugging Face.
- Topic: extraction of legislation, case law, people, time, location and organizations from legal texts.
- Results: F1 of 81.42% for the small model and 83.76% for the large model.
- Technical highlight: applied legal NLP, comparative evaluation and a usable end-user deliverable.
CNN for COVID-19 support in chest X-ray diagnosis
In my MBA thesis, I developed and validated a convolutional neural network model to classify chest X-ray images with a focus on supporting COVID-19 diagnosis.
- Dataset built with 2,089 images, including 505 COVID-19 cases and 1,580 normal cases.
- Results: 98.40% test accuracy, with hyperparameter tuning and data augmentation.
- Technical highlight: deep learning applied to healthcare, experimental design and public code on GitHub.
Where to Find Me
Projects, publications and technical presence
LinkedIn
Publications, articles and professional positioning.
GitHub
Code, experiments and technical paths connected to my practice.
Kaggle
Notebooks, challenges and applied data science exercises.
Hugging Face
AI exploration, models and experiments connected to the open-source ecosystem.
Medium
Original content on graphs, Spark, Python, statistics and AI libraries.
Contact
Get in touch and let’s talk
I am always open to new opportunities.