Bradley Mcdanel
Assistant Professor Of Computer Science at Franklin & Marshall College
Pennsylvania, United States
Summary
👤
Senior🎓
Top SchoolBradley Mcdanel is an assistant professor of computer science at Franklin & Marshall College with 12 years of experience bridging deep learning research and hardware-aware systems. His work focuses on decomposing neural network computation to the bit level—representing ops as sums of powers-of-two—to expose novel opportunities for accelerating DNN training and inference through compression, quantization, and adaptive computation. He brings a strong co-design perspective, developing compilers, scheduling techniques for systolic architectures, and neural architectures tailored to specialized hardware from a foundation of PhD research and postdoctoral work at Harvard and internships at Intel. Bradley’s background in networking research and early app development for special-needs users shows a breadth that informs practical, real-world system design choices. Based in Pennsylvania, he combines rigorous academic scholarship with hands-on systems prototyping to push efficient AI from theory toward deployable hardware-software stacks.
12 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Harvard UniversityMaster of Science (M.S.), Computer Science, Master of Science (M.S.), Computer Science at Wake Forest University
Github Skills (35)
python10
feedforward10
gpu10
c-library10
numpy9
machine-learning9
neural-network9
deep-learning9
gpu-acceleration8
autograd8
inference8
tensor8
pytorch7
reinforcement-learning7
networking6
Programming languages (5)
Github contributions (5)
BradMcDanel/cps242-assignments
Feb 2022 - Jan 2023
Contributions:38 commits, 37 pushes, 1 branch in 11 months
kunglab/ebnn
Nov 2016 - Sep 2018
Header-only C library for Binary Neural Network Feedforward Inference (targeting small devices)
Contributions:81 commits, 1 PR, 24 pushes in 1 year 10 months
c-libraryfeedforwardinferenceneural-networkembedded-devices
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.