Hi, I'm Thiago Barbieri 👋

Data Scientist | Machine Learning & AI Engineer | AI Researcher, based in São Carlos, Brazil.

• 🎓 Direct Ph.D. student in Artificial Intelligence at ICMC-USP (since Aug 2025)
• 🎓 BSc in Computer Engineering, UFSCar (2019 – 2024)
• 💼 Previously at Newfoundland Capital Management (2022 – 2025): Data Scientist Intern, Quantitative Analyst, and technical coordinator of an EMBRAPII-funded generative AI project

What I work with

• Data & ML: end-to-end ETL pipelines, web data acquisition, predictive modeling and time series forecasting for financial and macroeconomic data, dashboards and analytics tools
• LLMs & GenAI: LLM-based agents, RAG, GraphRAG and LLMOps; I coordinated a conversational robo-advisor for Brazilian investors (FastAPI, LangChain, Qdrant, BERT/BERTimbau, OR-Tools for portfolio optimization)
• Cloud & infrastructure: AWS (Lambda, S3, DynamoDB, API Gateway, EventBridge, CloudWatch), Kubernetes (K3s), Terraform, Argo CD, GitLab CI/CD

Tech stack

Languages: Python, SQL, R, C, C++, C#
Data & ML: Pandas, Polars, PySpark, scikit-learn, PyTorch, TensorFlow/Keras, Hugging Face
Tools: FastAPI, LangChain, Docker, Git, GitHub Actions, Streamlit, Dash, Plotly

Currently

• 🔭 Researching Artificial Intelligence as a Ph.D. student at ICMC-USP
• 🌱 Studying LLMOps, GraphRAG, knowledge graphs for GenAI, and data engineering with Databricks and Spark

About this repository

My intention is to use this repository to save some of my extra studies.