Skip to content
View guerrajorge's full-sized avatar

Block or report guerrajorge

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
guerrajorge/README.md

Hi, I'm Jorge Guerra 👋

ML Engineer · Data Scientist · Entrepreneur · Builder

I've spent the last 10+ years building ML systems, data platforms, and products that solve real problems — from saving banks millions with predictive models to deploying cardiovascular risk tools used by 500K+ people. My work spans machine learning, NLP, full-stack development, and mobile apps across banking, healthcare, research, and tech startups.

I'm equally comfortable building frontend interfaces, designing backend architectures, writing Python pipelines, or automating complex workflows end-to-end.

LinkedIn Portfolio Email


🚀 What I'm Building Now

Project Role Description
🧬 Onkopilot Co-Founder & CTO AI-powered oncology support platform using RAG & LLMs to guide cancer patients and caregivers
🏅 Xsporty Co-Founder & CTO Sports community app connecting athletes, coaches, and facilities in Puerto Rico
🦷 My Dental Path CTO Platform helping international dentists navigate US dental school admissions

💼 Experience Highlights

Data Scientist Program Lead @ Popular Bank (2023 – Present)

  • 💰 Saved $58M by building a tool to classify claimed vs. unclaimed properties
  • 💰 Saved $300K/year with an ML-based loan portfolio valuation model
  • 📉 Reduced AML analyst workload by 10X with an XGBoost-powered alert detection system

Data Scientist @ One Drop (2021 – 2022)

  • 🫀 Developed a cardiovascular risk model deployed to 500K+ users with diabetes

Senior Data Scientist @ KPMG (2019 – 2021)

  • 🏥 Built NLP + OCR pipeline automating 10,000+ manual medical record reviews

Data Scientist @ Children's Hospital of Philadelphia (2017 – 2019)

  • 🏆 Won the Drexel LeBow Analytics 50 Award for patient no-show prediction model
  • 🔬 Published at ACL CLPsych 2019 and IEEE EMBS 2018

🧠 Skills & Stack

Languages: Python · SQL · R · C# · MATLAB · Java

ML / AI: Scikit-learn · XGBoost · LightGBM · TensorFlow · PyTorch · SVMs · HMMs · Ensemble Methods

NLP: spaCy · NLTK · BioBERT · ClinicalBERT · Transformers · NER · Topic Modeling

GenAI: LLMs · RAG · LangChain · OpenAI API · Claude · Prompt Engineering · Fine-tuning

Cloud & Infra: AWS · Azure · Databricks · Docker · Git · CI/CD

Mobile & Web: Flutter · Dart · Firebase · Next.js · iOS · Android

Visualization & BI: Power BI · Tableau · Plotly · Matplotlib


📄 Selected Publications


🎓 Education & Honors

🎓 M.S. Data Science — Columbia University (GEM Fellow)
🎓 B.S. Computer Engineering — University of Central Florida (McNair Scholar · Dean's List)

🏆 Analytics 50 Award — Analytics Magazine, 2018
🏆 GEM Fellowship — National GEM Consortium, 2014
🏆 McNair Scholar — Ronald E. McNair Program, 2013


📍 Based in San Juan, Puerto Rico · Open to Consulting

If you have a project that involves ML, NLP, data platforms, or full-stack product development — let's talk.

Popular repositories Loading

  1. WebBot WebBot Public

    Wikipedia WebBot + questions and answers creation

    C# 3

  2. clpsych clpsych Public

    Jupyter Notebook 3 1

  3. METACHOP METACHOP Public

    HTML 1

  4. libpomdp libpomdp Public

    Forked from mgrzes/libpomdp

    libpomdp is a set of POMDP approximation algorithms implemented in Java and Matlab

    MATLAB

  5. deadlywheels deadlywheels Public

    Senior Design Project

    Java

  6. opencv opencv Public

    Forked from opencv/opencv

    Open Source Computer Vision Library

    C++