Matheus Pedroni is a data scientist with eight years of experience building production-ready ML solutions, from exploratory prototypes to scalable ETL pipelines and inference APIs. He has improved forecasting and pricing models at scale—delivering 10x speedups in data processing—and has hands-on expertise in PySpark, scikit-learn, PyTorch and FastAPI. His background in molecular biology and biomedical training gives him a strong statistical mindset and an ability to translate complex data into product-focused insights for stakeholders. Recently he has been exploring LLMs and generative AI, shipping projects like llm-docsmith for automatic Python docstrings and mcp-ols to augment LLMs with regression tools. Based in Vinhedo, Brazil, he maintains a technical blog (mathpn.com) and brings a pragmatic blend of research rigor and production engineering to data-driven products.
8 years of coding experience
1 year of employment as a software developer
Mestrado Biologia Molecular, Mestrado Biologia Molecular at Universidade Estadual de Campinas
Bacharelado Biomedicina, Bacharelado Biomedicina at Unifesp - Universidade Federal de São Paulo
Contributions:9 releases, 20 PRs, 81 pushes in 2 years
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.