Cosmin Petra is a computational mathematician with 19 years of experience developing scalable algorithms and parallel solvers for complex engineering systems, currently at Lawrence Livermore National Laboratory. He specializes in optimization under uncertainty, high-performance computing, parallel methods for optimization and linear algebra, and security-constrained AC power flow, with hands-on expertise in C/C++, Julia, MPI, OpenMP and CUDA. His contributions to flagship open-source projects like SUNDIALS and MFEM—adding sensitivity analysis to IDAS and integrating the HIOP optimizer—reflect a focus on making advanced numerical methods production-ready and portable. Past roles at Argonne and as an adjunct professor demonstrate a strong research-to-practice trajectory and mentoring experience. Colleagues rely on him for tackling large-scale constrained optimization and nonlinear systems where performance, robustness, and rigorous mathematics intersect.
Lightweight, general, scalable C++ library for finite element methods
Role in this project:
Back-end Developer
Contributions:4 reviews, 22 commits, 1 PR in 4 years 6 months
Contributions summary:Cosmin primarily contributed to the integration of the HIOP (High-Order Interior-Point Optimizer) solver within the MFEM library. Their work involved adding initial files for the HIOP solver, updating the CMake build system to correctly handle HIOP dependencies, and developing the interface class. Furthermore, the user completed the proposed interface, ensuring that the MFEM library could utilize the HIOP solver for optimization tasks. These changes suggest a focus on enhancing MFEM's capabilities for numerical optimization.
Official development repository for SUNDIALS - a SUite of Nonlinear and DIfferential/ALgebraic equation Solvers. Pull requests are welcome for bug fixes and minor changes.
Role in this project:
Backend Developer
Contributions:20 commits in 2 months
Contributions summary:Cosmin contributed significantly to the SUNDIALS solver library, a project focused on solving nonlinear and differential/algebraic equations. Their work centered on implementing sensitivity analysis capabilities within the IDAS (Implicit Differential-Algebraic Solver) module. Key contributions include the addition of dense output functions for various solution components, updates to function prototypes, and the development of example problems to demonstrate the new functionality.
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.