Joaquim Lyrio is a Staff Data Scientist with a decade of experience building production ML systems and leading cross-functional teams across fintech, mobility, health tech, and energy. He combines rigorous statistical training (MA Statistics, Columbia) with hands-on engineering—authoring pipelines in Spark, deploying churn and LTV models at scale, and shipping recommendation and optimization algorithms that improved KPIs and operational efficiency at Uber. At Sword Health he was the first data scientist in his team, owning end-to-end model development for surgical detection and cost estimation; earlier roles span energy systems optimization and large-scale financial forecasting. He contributes to open-source scientific tooling as a backend developer on the JuMP.jl ecosystem, improving solver integrations and tutorials for mathematical optimization. Known for turning noisy, multi-source data into reliable decisioning pipelines, he thrives on problems that blend optimization, forecasting, and scalable ML infrastructure.
10 years of coding experience
7 years of employment as a software developer
Pontifical Catholic University of Rio de Janeiro
MA Statistics, MA Statistics at Columbia University
Exchange student for one semester, Exchange student for one semester at UC Santa Barbara
Modeling language for Mathematical Optimization (linear, mixed-integer, conic, semidefinite, nonlinear)
Role in this project:
Back-end Developer
Contributions:110 reviews, 29 commits, 36 PRs in 5 years
Contributions summary:Joaquim primarily contributed to the improvement of Xpress solver integration, adding documentation and tests. They modified solver-related files and updated installation instructions. The user introduced a new `fix` function within the `JuMP` module, deprecating the `setvalue` behavior for fixed variables, and made associated documentation changes. Additionally, they added tutorial content for a facility location problem.
Contributions:49 commits, 20 PRs, 41 pushes in 1 year 11 months
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.