Greg Devosnouri
Learned Autonomy Technical Lead at EpiSci (an Applied Intuition company)
San Diego, California, United States
Summary
🤩
Rockstar🎓
Top SchoolGreg Devosnouri is a technical lead specializing in learned autonomy for fixed-wing systems, currently advancing group 5 aircraft capabilities at EpiSci in San Diego. With eight years in software and AI engineering, he has moved from embedded systems and real-time avionics at Northrop Grumman to leading autonomy research and productization, including scaling GNN-based time-series prediction systems that dramatically reduced latency. He blends hands-on engineering—backend contributions to the popular darts time-series library and strong code-quality practices—with program leadership, mentorship, and IRAD stewardship over multi-engineer teams and million-dollar efforts. Comfortable across embedded RTOS, GPU/OpenCL pipelines, containerized services, and ML research, he connects low-level system constraints to production ML solutions. A builder since childhood, he pairs pragmatic system design with a knack for improving developer workflows and reproducible model management.
8 years of coding experience
11 years of employment as a software developer
Master's degree, Computer Science, Master's degree, Computer Science at Georgia Institute of TechnologyBachelor of Engineering (BEng), Computer Engineering, Bachelor of Engineering (BEng), Computer Engineering at Cedarville University
Github Skills (10)
forecasting10
machine-learning10
forecast10
time-series10
python10
data-science9
anomaly-detection9
deep-learning8
isort8
deeplearning-ai8
Programming languages (4)
Github contributions (5)
unit8co/darts
Feb 2022 - Nov 2022
A python library for user-friendly forecasting and anomaly detection on time series.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:43 reviews, 21 commits, 30 PRs in 9 months
Contributions summary:Greg primarily contributed to the backend of the "darts" library, focusing on enhancements and bug fixes related to model management and code quality. They added unique identifiers to model names and addressed isort and pyupgrade issues, indicating a focus on code maintainability and import organization. The user also worked on fixing typos and improving code formatting.
forecastingpython-libraryanomalypythontime-series-analysis
gdevos010/darts
Jan 2022 - Sep 2024
A python library for easy manipulation and forecasting of time series.
Contributions:6 PRs, 190 pushes, 114 branches in 2 years 8 months
forecastingmanipulationpython-librarypythontime-series-analysis
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.