👋 Hi, I’m Corey

🎓 Academic Path

Bachelor of Science in Software Development (Web & Mobile Applications) – DeVry University

Future Master’s in AI Engineering – University of Pennsylvania

Future Ph.D. in Artificial Intelligence – research in advanced machine learning, LLMs, and AI systems

💻 GitHub Portfolio Highlights

Facial Emotion Recognition System – CNN-based model with accuracy metrics & visualizations

Quant LLM Assistant – Hugging Face + LangChain powered assistant with retrieval-augmented generation

Disease Prediction Capstone – ML pipeline with preprocessing, EDA, training, and evaluation

AI Vehicle Safety Classifier – Python + C++ dual implementation with performance comparisons

🛠️ Skills & Tools

Programming: Python, C++, Java, C#, SQL

AI/ML Frameworks: TensorFlow, PyTorch, scikit-learn, LangChain, Hugging Face

DevOps & Cloud: AWS, Docker, CI/CD, Ansible

Data Visualization: Matplotlib, Seaborn, Plotly

🚀 Career Goals

I am pursuing a career as an AI/ML Engineer, with a focus on:

Building production-ready AI systems

Advancing LLMs, Deep Learning, and System Design

Contributing to Big Tech & Big AI companies such as OpenAI, NVIDIA, Meta, and Google DeepMind

🌍 Purpose

I aim to use AI not only to advance technology but to change lives — from improving healthcare and infrastructure to creating safe, ethical, and impactful AI systems.

📫 Connect with me on LinkedIn

Linkedin.com/corey-leath

Core ML Algorithms:

• ✅ Linear Regression (price prediction)
• ✅ K-Nearest Neighbors (pattern similarity)
• ✅ Gradient Boosting (portfolio forecasting)

Core ML Algorithms:

• ✅ Convolutional Neural Networks (deep learning backbone)
• ✅ K-Means Clustering (unsupervised feature grouping)
• ✅ Gradient Boosting (tabular benchmark)

Core ML Algorithms:

• ✅ Random Forest (tabular safety classification)
• ✅ K-Nearest Neighbors (incident similarity)
• ✅ Gradient Boosting (boosted safety predictions)

Core ML Algorithms:

• ✅ Linear Regression (time-based forecasting)
• ✅ Random Forest (multi-variable regression)
• ✅ Gradient Boosting (advanced time-aware modeling)

Core ML Algorithms:

• ✅ Random Forest (cloud-optimized classifier)
• ✅ Gradient Boosting (via SageMaker XGBoost)
• ✅ K-Means Clustering (energy user grouping)

Core ML Algorithms:

• ✅ Linear Regression (strategy return prediction)
• ✅ K-Means (cluster strategies)
• ✅ Random Forest (ensemble modeling)
• ✅ K-Nearest Neighbors (market behavior similarity)

🔗 Visit my GitHub: Trojan3877

👉 Next steps:

• Create the special repo: Trojan3877/Trojan3877 and add this as README.md.
• Replace placeholders (your-linkedin, repo names/links if slightly different).
• This instantly makes your GitHub profile look like a curated portfolio site.

⚡ Question for you: do you want me to now generate the individual README upgrades for each repo (FER, Quant LLM, AWS Pipeline, ER Triage) one by one — each with Results tables, Quickstart blocks, and sample visuals baked in?