Francesco Petrini
Systems Software Engineer at NVIDIA
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolFrancesco Petrini is a systems software engineer based in San Francisco with nine years of experience building C++ and Python systems across medical devices, machine learning research, and full-stack development. Currently at NVIDIA, he brings production-grade backend experience—highlighted by contributions enabling Python model testing in the widely used Triton Inference Server—to large-scale inference and ML infrastructure. His prior work at Abbott focused on safety-critical embedded systems, including encryption frameworks for cardiac devices and development of a dual-chamber leadless pacemaker, demonstrating deep domain expertise in multithreaded C++ and regulatory-grade documentation. He pairs strong technical delivery with teaching and mentorship experience from UC Davis and Abbott, refining his ability to explain complex systems clearly. Francesco combines rigorous academic training (MS in Computer Science, 4.0 GPA) with practical tooling and verification skills, making him adept at moving research prototypes into robust production software.
9 years of coding experience
4 years of employment as a software developer
Master's degree, Computer Science, 4.0/4.0, Master's degree, Computer Science, 4.0/4.0 at University of California, DavisBachelor of Science - BS, Computer Science and Engineering Major with a Minor in Mathematics, 3.5/4.0, Bachelor of Science - BS, Computer Science and Engineering Major with a Minor in Mathematics, 3.5/4.0 at Santa Clara UniversitySt. Ignatius College Preparatory
English, Italian
Github Skills (8)
machine-learning10
inference10
back-end-development10
python10
dockers7
docker7
cloud-computing6
gpu5
Programming languages (6)
Github contributions (5)
triton-inference-server/server
Jun 2022 - Sep 2022
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:196 reviews, 42 commits, 87 PRs in 2 months
Contributions summary:Francesco primarily contributed to the Python backend functionality within the Triton Inference Server, specifically adding Python backend support for the L0-batcher and L0-sequence-batcher components. Their work involved modifying existing test scripts and creating/modifying configuration files to integrate Python models. This included changes to test configurations and model handling to accommodate the Python backend within the existing testing framework. The user's contributions enabled the testing of Python models within the Triton Inference Server environment.
nvidia-dockernvidiadeep-learninggpuinference
fpetrini15/Coen174_Webpage
Oct 2018 - Nov 2018
Alumni engagement page created as a project for Coen 174 (software engineering)
Contributions:43 pushes, 1 branch in 1 month
reactalumnijavascriptcoennodejs
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.