Salma Mayorquin is a Co-Founder and machine learning engineer with nine years of experience building production-ready AI and data systems from prototype to deployment in the San Francisco Bay Area. At Remyx AI she helps non-experts customize and train deployment-ready models without code, drawing on prior roles at Databricks where she guided clients on ML/Deep Learning architectures and at Heritage where she built HIPAA-compliant AWS pipelines and search applications. A hands-on developer and hardware tinkerer, Salma contributes to open-source ML projects like ActionAI—improving pose-based activity recognition with LSTMs and data augmentations—and runs a consulting practice, Smells Like ML, that delivers practical ML solutions and demos. She pairs an applied mathematics background from UC Berkeley with a knack for translating researchy models into usable products, and she’s equally comfortable debugging model training pipelines as prototyping robotics and embedded systems.
9 years of coding experience
3 years of employment as a software developer
Bachelor's degree Applied Mathematics, Bachelor's degree Applied Mathematics at University of California, Berkeley
Real-Time Spatio-Temporally Localized Activity Detection by Tracking Body Keypoints
Role in this project:
ML Engineer
Contributions:34 commits, 47 pushes, 1 branch in 11 months
Contributions summary:Salma primarily worked on developing and refining machine learning models for human activity recognition. Their contributions include fixing issues in data loading and model training, along with adding new functionalities such as a notebook for identifying yoga poses with KNN. The user also implemented augmentations for pose data to improve model performance and designed the training and utilization of LSTM models for action detection.
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.