Summary
Pedro Valero-Lara is a Senior Computer Scientist at Oak Ridge National Laboratory with a PhD in Computer Science and Applied Mathematics and over a decade of experience building high-performance scientific software. He focuses on parallel programming models, math libraries, performance portability, and software sustainability across heterogeneous DOE HPC systems, and co-leads the S4PST project to unify efforts across LLVM, OpenMP/OpenACC, Kokkos, Fortran, and Julia communities. Pedro has contributed to flagship DOE and vendor libraries (Kokkos, PLASMA, LibSci-ACC, cuSparse, IRIS-SDK), blending deep numerical expertise with practical engineering to boost performance and productivity. Recently he has been pioneering the integration of generative AI into HPC programming workflows to accelerate scientific software development. His background spans research and industry roles at Barcelona Supercomputing Center, Cray, NVIDIA, and multiple academic institutions, giving him a rare mix of applied research and production library experience. Based in Knoxville, Tennessee, he brings a sustained track record of turning low-level optimization and tooling work into widely used, portable scientific software.
9 years of coding experience
14 years of employment as a software developer
Master's degree Computer Science, Master's degree Computer Science at Universidad de Castilla-La Mancha
Doctor of Philosophy - PhD Computer Science and Applied Mathematics, Doctor of Philosophy - PhD Computer Science and Applied Mathematics at Universidad Complutense de Madrid