Harvey Caicedo
Supreme Commander at Ganadería Memphis
Colombia
Summary
👤
Senior🎓
Top SchoolHarvey Caicedo is an open-source software developer and entrepreneur with 11 years of experience bridging electronics engineering, evolutionary computation and applied machine learning. As founder of Ingeni-us Ingeniería and Supreme Commander at Ganadería Memphis, he combines hands-on web and telecom systems development with practical industrial and agricultural operations—running projects from SCADA backups to farm management. His research-driven master's focus on evolutionary computation informs work like Singularity, a decentralized, blockchain-backed optimization platform, and Gym-Forex, an OpenAI Gym environment for Forex simulation. He has delivered embedded and networked solutions in industrial settings and led engineering teams as CTO, showing both low-level systems skill and web architecture fluency. Based in Colombia, Harvey blends academic rigor with entrepreneurial grit, often embedding AI into real-world, traceable optimization workflows. A lesser-known strength is his habit of pairing field-level insights from high-altitude farming with algorithmic innovation to build resilient, production-ready systems.
11 years of coding experience
4 years of employment as a software developer
Master’s Degree, Systems Engineering, Master in Engineering, Master’s Degree, Systems Engineering, Master in Engineering at Pontificia Universidad JaverianaIngeniero Electrónico, Ingeniero Electrónico at Universidad San Buenaventura - Cali
English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (111)
transformers10
evolutionary10
trainer10
python10
feature-extraction10
optimizers10
trading10
simulator10
attention-mechanism10
cnn-keras10
feature-engineering10
datasets10
regression10
evaluator10
p2p-node10
Programming languages (4)
Github contributions (5)
harveybc/feature-extractor
Oct 2018 - Jul 2021
Application for training an autoencoder for generating an encoder that can be used as feature extractor for dimensionality and noise reduction, while the decoder can be used for synthetic data generation. Supports dynamic plugin integration, allowing users to extend its capabilities by adding custom encoder and decoder models.
Contributions:1042 commits, 53 PRs, 1614 pushes in 2 years 9 months
web-interfacefeature-basedserverlesstrainingtrainer
harveybc/predictor
Nov 2014 - Nov 2020
Predictor that uses a configurable plugin-based predictive supervised learning model, to make forecasts for a configurable time horizon in a timeseries, using heterogeneus multivariate timeseries data as input, the input data needs to be aligned with the timeseries to be used as training signals. Includes 4 built-in deep-learning predictive models.
Contributions:440 commits, 64 PRs, 2864 pushes in 6 years 1 month
web-platformsqlitevisualizingbuilt-inmultiuser
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.