Data Scientist with a Bachelor's degree from Vila Velha University (UVV), focused on applying analytical solutions and advanced techniques to solve real-world problems and generate value for businesses and organizations.

Implementation of full machine learning pipelines, deployment automation, and integration of DevOps practices for scalable data systems.

Key practices include:

• MLOps Pipelines: Data preprocessing, training, hyperparameter tuning, deployment and monitoring.
• CI/CD for ML: GitHub Actions workflows, automated testing (Pytest), continuous deployment.
• Containerization: Packaging ML applications with Docker for reproducibility and scalability.

Projects:

• MLOps Customer Churn Project
• Credit Risk Web Application
• MLOps with Naive Bayes

Real-life applications using supervised and unsupervised learning, neural networks and advanced modeling techniques.

• Credit Risk Web Application
• Churn Analysis
• Recommender System
• Campaign Optimization
• Customer Segmentation
• Time Series Benchmark Project
• Recommender System with PySpark
• Fraud Detection With Deep Learning
• Logistics Web Application

Applications of generative models, fine-tuning, and retrieval-augmented generation techniques.

• AI Multi-Agents
• Specialized Chatbot with RAG and LangChain

Causal econometrics and inference methods to support decision-making and policy evaluation.

• Causal Inference with RDD
• Delinquency Policy Evaluation Project

Identification of patterns, trends, and insights through exploratory techniques.

• EDA with Power BI and R

• Extracting structured/unstructured data
• Automating desktop tasks
• Building ETL processes for analytics and reporting

Projects:

• Sales Report Automation
• Web Scraping Projects
• Automation with PyAutoGUI

• Python
• R
• SQL

• AWS (ECR + ECS Fargate, EC2, EKS Lambda, S3, CloudWatch)
• Databricks
• PySpark

• Docker
• Airflow
• CI/CD (GitHub Actions)
• MLflow
• Monitoring (Prometheus, Grafana)
• Pytest
• Flask, FastAPI

• Supervised & Unsupervised Learning
• Deep Learning
• Generative AI
• Time Series Modeling
• Causal Inference & Econometrics

• Power BI
• Tableau
• Excel
• Streamlit

• Git, DVC

• Proactivity and endless curiosity
• Critical thinking and adaptability
• Problem-solving
• Teamwork
• Familiarity with agile methodologies

I am seeking opportunities where I can:

• Continuously learn
• Contribute to relevant projects
• Transform data into intelligent and strategic decisions

• LinkedIn: Higor Caetano
• Medium: @higorfct