Summary
Paulo Chagas is a data scientist with 11 years of experience translating research-grade deep learning and statistical methods into production AI systems. He combines a strong academic background in computer vision and uncertainty estimation with hands-on expertise deploying models and pipelines on AWS, Docker, and modern data stacks. At QuintoAndar and Loggi he led experiments and built GenAI and vision-driven solutions that delivered measurable business impact, including a 62% conversion uplift and a 97% accurate condo-bill extraction engine. Comfortable across the full ML lifecycle, he pairs rigorous experimentation (A/B testing, power analysis) with scalable engineering (DBT, Airflow, PySpark) and clear data storytelling for non-technical stakeholders. An active researcher with peer-reviewed publications from his lab work, he brings a habit of scientific rigor and test-time robustness into product settings. Based in Bahia, Brazil, he’s currently focused on advancing computer vision, deep learning, and AI agents while rapidly learning new tools to solve unfamiliar problems.
10 years of coding experience
8 years of employment as a software developer
Brazil Scientific Mobility Program Student Computer Science, Brazil Scientific Mobility Program Student Computer Science at Indiana University Bloomington
Master's degree Computer Science, Master's degree Computer Science at Universidade Federal do Pará
Portuguese, English