Bryan Lozano
Principal Software Engineer at Tenstorrent
San Jose, California, United States
Summary
👤
Senior🎓
Top SchoolBryan Lozano is a Principal Software Engineer based in San Jose with a decade of experience building high-performance ML and FPGA-accelerated systems. He has driven measurable impact at companies like Xilinx and Tenstorrent—boosting inference throughput by 25% and extending runtimes (e.g., TVM) for RyzenAI-class platforms. Skilled in C++, Python, FPGA toolchains, and cloud-native ML deployment, he blends deep hardware knowledge with production ML engineering and model optimization. Bryan is also an active educator and content creator—contributing popular Jupyter tutorials, LeetCode Legends algorithm content, and enhancements to Xilinx ML Suite demos that streamline model deployment. Pursuing an MS in Computer Science at Georgia Tech, he pairs rigorous academic training with hands-on product delivery for edge and datacenter inference. His background in both field applications and core engineering gives him a rare ability to translate customer requirements into optimized, deployable ML solutions.
10 years of coding experience
15 years of employment as a software developer
BS Electrical Engineering, BS Electrical Engineering at Rochester Institute of TechnologyMaster of Science - MS Computer Science, Master of Science - MS Computer Science at Georgia Institute of Technology
Github Skills (12)
machine-learning10
caffe10
xilinx10
python10
scripting9
jupyter-notebook9
shell9
script9
sh9
computer-vision9
mlops8
javascript8
Programming languages (11)
Github contributions (5)
Xilinx/ml-suite
Jul 2018 - Sep 2019
Getting Started with Xilinx ML Suite
Role in this project:
ML Engineer
ML EngineerContributions:145 commits, 11 PRs, 151 pushes in 1 year 2 months
Contributions summary:Bryan primarily contributed to the Xilinx ML Suite by adding support for a perpetual demo, which involved modifications to shell scripts, Python scripts, and JavaScript files within the `apps/perpetual_demo` directory. They updated the `run.sh` script and made changes to the `xfdnn` library. Additionally, the user updated several Jupyter Notebooks related to image classification and object detection with YOLOv2, including the integration of automated batch normalization merging in the YOLOv2 notebook. These changes suggest a focus on enhancing and optimizing machine learning model deployment and execution within the Xilinx environment.
xilinxsuitemachine-learning
wilderfield/XRT
Dec 2020 - Apr 2024
Xilinx Run Time for FPGA
Contributions:2 PRs, 4 pushes, 3 branches in 3 years 4 months
xilinxfpga
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.