Alex Stoken
Data Scientist
Houston, Texas, United States
Summary
👤
Senior🎓
Top SchoolAlex Stoken is a data scientist with nine years of experience applying computer vision and remote sensing techniques to space and earth-science problems, currently at Amentum supporting NASA missions. He blends rigorous academic training (MS CS from UT Austin; physics and math background from University of Arizona) with hands-on ML engineering—contributing to high-profile open-source projects like YOLOv5 and CNN visualization tooling to improve training, logging, and visualization workflows. His work spans production-focused model training, experiment tracking, and image-generation enhancements, with a particular interest in 3D computer vision, localization, and using data for social good. Alex has practical experience in high-stakes scientific environments (CERN, NASA internships) and in teaching/mentoring large online graduate classes. He uniquely pairs domain knowledge in physics and remote sensing with software engineering discipline to deliver reproducible ML pipelines for space imagery. Based in Houston, he brings a measured focus on experiment rigor and interpretable visualizations to mission-critical computer vision tasks.
9 years of coding experience
1 year of employment as a software developer
The University of ArizonaMaster of Science - MS Computer Science, Master of Science - MS Computer Science at The University of Texas at AustinBachelor of Arts - BA Economics, Bachelor of Arts - BA Economics at University of Arizona - Eller College of ManagementValedictorian, Valedictorian at Mountain Pointe High School
English, Spanish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (11)
object-detection10
computer-vision10
pytorch10
machine-learning10
deep-learning10
python10
image-processing10
yaml10
deeplearning-ai9
mlops9
tensorboard9
Programming languages (4)
Github contributions (5)
utkuozbulak/pytorch-cnn-visualizations
Feb 2020 - Mar 2020
Pytorch implementation of convolutional neural network visualization techniques
Role in this project:
ML Engineer
ML EngineerContributions:23 commits, 1 PR, 3 comments in 29 days
Contributions summary:Alex primarily contributed to image generation techniques within the repository, focusing on convolutional neural network visualization. They added features like Gaussian blur, weight decay, and gradient clipping to enhance image quality. Key changes included modifying image saving locations, introducing a file to record generation process details, and refactoring the image preprocessing function.
camguided-grad-camgrad-camconvolutional-neural-networksegmentation
ultralytics/yolov5
Jun 2020 - Aug 2020
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
Role in this project:ML Engineer
ML EngineerContributions:4 PRs, 19 comments in 2 months
Contributions summary:Alex primarily contributed to the training and logging aspects of the YOLOv5 object detection model. Their work involved adding arguments for hyperparameter files, saving training options and hyperparameters to the TensorBoard log directory, and modifying the directory structure for saving weights and results. The user also implemented functionality to plot the learning rate scheduler and other training results, along with enhancements for resuming training runs. These changes are aimed at improving the model's training process and experiment tracking.
pytorchdeep-learningyolov8object-detectionmachine-learning
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.