Javier聽Porras-valenzuela
Machine Learning Engineer
Philadelphia, Pennsylvania, United States
Summary
馃懁
Senior馃帗
Top SchoolJavier Porras-valenzuela is a Machine Learning Engineer with 10 years of experience building and productionalizing large-scale ML and deep learning systems across logistics, demand forecasting, retail and fraud detection. Trained summa cum laude with an MSc in Computer Science, he combines research-driven approaches with hands-on implementation鈥攐ften writing custom ML algorithms in Apache Spark using Python, Scala and Java. He has led client-facing consulting projects and headed a team that deployed a supply chain optimizer to production, demonstrating strength in turning academic ideas into operational solutions. Javier also teaches and mentors, having delivered deep learning instruction in a professional AI program, and is particularly interested in graph neural networks, reinforcement learning and stochastic optimization. Based in Philadelphia, he blends R&D curiosity with practical engineering discipline, favoring scalable data pipelines and tailored algorithmic solutions that address real business constraints.
10 years of coding experience
8 years of employment as a software developer
Master of Science - MS, Computer Science, summa cum laude, Master of Science - MS, Computer Science, summa cum laude at Tecnol贸gico de Costa RicaBachelor's degree, Systems Engineering, Bachelor's degree, Systems Engineering at Universidad Nacional de Costa Rica
Spanish, English, Japanese
Github Skills (46)
decomposition9
autoencoder9
correlation9
arxiv9
genome8
time-series-forecasting8
abstract-syntax-tree7
genetic-algorithm7
compile7
cactus7
deep-learning6
time-series6
java6
compile-time6
vertex6
Programming languages (5)
Github contributions (5)
jotaporras/ts_mcfrl
May 2020 - May 2022
Repo para experimentos de tema selecto con multicommodity flows + RL
Contributions:7 PRs, 101 pushes, 7 branches in 2 years
conreinforcement-learningflowstema
ihounie/Autoformer
Aug 2023 - Feb 2025
About Code release for "Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting" (NeurIPS 2021), https://arxiv.org/abs/2106.13008
Contributions:1 PR, 59 pushes, 2 branches in 1 year 5 months
Find and Hire Top DevelopersWe鈥檝e 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.