Justin Davis
Graduate Research Assistant
California, United States
Summary
🤩
Rockstar🎓
Top SchoolJustin Davis is a PhD student and graduate research assistant at the Colorado School of Mines with nine years of engineering experience focused on embedded and autonomous systems, computer vision, and hardware-accelerated machine learning. He designs and evaluates multi-accelerator DNN pipelines and robot planning systems, maintaining lab infrastructure from server-grade rigs to NVIDIA Jetson, Xilinx Kria, and Google Coral devices. Justin combines hands-on system design—specifying cost- and maintainability-conscious workstations—with experiment-driven analysis of energy, latency, and throughput for real-world CV and robotics workloads. He also teaches heterogeneous computing and operating systems topics, mentoring students in CUDA, TensorRT, FPGA toolchains, and performance-oriented software. Notably, his background spans applied industry work (optimizing an analytical color sorter and mining engineering automation) through to advanced research in accelerator-aware DNN pruning and concurrent inference.
9 years of coding experience
1 year of employment as a software developer
Associate of Arts in Liberal Sciences, Associate of Arts in Liberal Sciences at University of Maine at Presque IsleDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Colorado School of MinesHigh School Diploma, High School Diploma at Maine School of Science and Mathematics (MSSM)
Github Skills (42)
object-tracking10
python10
image-classification10
semantic-segmentation10
machine-learning10
yolov810
pose-estimation10
object-detection10
computer-vision10
pytorch9
jetson9
instance-segmentation9
deep-learning9
ultralytics9
nvidia9
Programming languages (5)
Github contributions (5)
justincdavis/trtutils
Nov 2023 - May 2026
Quickly and easily use TensorRT inside of Python with support for models out-of-the-box
Contributions:21 releases, 111 PRs, 546 pushes in 2 years 6 months
pythontensorrtdnn-inferenceimage-classificationinference
AutonoLab/pteranodon
Jun 2022 - Mar 2023
A framework to built on top of MAVSDK which provides physical/virtual drone abstraction, abstraction for all async calls, gives the end users an arduino-eqsue interface, and provides movement and utility methods based on relative cordinate systems.
Contributions:1 release, 72 reviews, 107 commits in 9 months
arduinoasyncpythondronedrones
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.