Open to opportunities

Hugo Rios

@hugorios

Message

I build Python ETL pipelines and risk-analysis tools for public-sector audit teams.

Brazil

Message

What I'm looking for

I'm seeking remote data-focused work where I can build ETL pipelines, automate analytical workflows, improve data quality, and apply Python, SQL, cloud services, and machine learning.

At the Tribunal de Contas dos Municípios da Bahia (TCM-BA), I build end-to-end ETL processes for semiannual selectivity and risk matrices used directly by audit teams.

I integrate internal Tribunal data with public sources including IBGE, applying cleaning, deduplication, business rules, and SQL to produce contract matrices and rankings. I also created a CLI generation workflow and an LLM-based validator that checks final matrices against documented rules while keeping calculations deterministic in code.

I maintain a web scraper integrated with the IAIÁ platform, collecting Google News and A Tarde content through RSS parsing, Selenium, Beautiful Soup, Pandas, and spaCy. I created an indicator for negative mentions of municipalities to support risk analysis and reduce continuous manual news monitoring.

I'm pursuing a Computer Science degree and have also implemented MLOps for Colmeia, a location-radius communication platform, using BERTimbau for 13-class content moderation.

Experience

Work history, roles, and key accomplishments

Estagiário de Análise de Dados

Tribunal de Contas dos Municípios da Bahia

Sep 2024 - Sep 2026 (2 years)

Developed a complete ETL process for semiannual selectivity and risk matrices used directly by audit teams. Integrated internal Tribunal data with public sources including IBGE, performing cleaning, deduplication, business rule application, and generation of contract matrices and rankings.

Python Pandas ETL SQL MySQL PostgreSQL Git AWS Sagemaker CLI Web Scraping Selenium SpaCy LLM Data Validation

Education

Degrees, certifications, and relevant coursework

Centro Universitário Jorge Amado

Bachelor of Science, Computer Science

2023 -

Pursuing a Bachelor's degree in Computer Science, currently in the 8th semester with expected completion around 2027. Coursework includes machine learning, data, software development, and databases.