Garrett Drapala
Hardware Architecture at NVIDIA
United States
Summary
👤
Senior🎓
Top SchoolGarrett Drapala is a hardware architect with 13 years of experience focused on microprocessor cache design, fabric coherency protocols, and RTL implementation and bring-up. He has driven high-impact architecture and RTL efforts at NVIDIA after senior engineering roles at Qualcomm and IBM, blending performance modeling with design automation to optimize cache and coherence behavior. Proficient in Verilog, VHDL and Python, he specializes in fault-tolerant, high-availability designs that translate complex protocols into robust silicon. Garrett also contributes to open-source tooling and docs—having improved pandas internals and documentation—underscoring a practical fluency across hardware and software. Based in the United States, he combines deep systems-level knowledge with hands-on lab experience, often surfacing subtle protocol interactions before tape-out. His background in Computer Engineering from RIT grounds a career-long interest in squeezing predictable performance from complex memory hierarchies.
13 years of coding experience
15 years of employment as a software developer
B.S., Computer Engineering, B.S., Computer Engineering at Rochester Institute of Technology
Github Skills (6)
pandas10
python10
documentation10
data-analysis10
testing9
data-science8
Programming languages (6)
Github contributions (5)
pandas-dev/pandas
Jan 2013 - Apr 2014
Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
Role in this project:
Technical Writer & Software Engineer
Technical Writer & Software EngineerContributions:10 commits in 1 year 2 months
Contributions summary:Garrett primarily contributed to the project by improving and updating the documentation, specifically by correcting merge suffixes and adding "kde" and "density" options to the plot kind docstrings. They also addressed an issue related to HTML escaping in the `to_html()` function and provided fixes for double escaping. Furthermore, the user made code changes to improve the tests and the general functionality of the `pandas` library, showcasing a good understanding of its internal workings.
pythondatalabeled-datamanipulationdataframes
gdraps/matplotlib-backend-sixelconv
Oct 2024 - Oct 2024
Contributions:3 pushes in 1 day
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.