I have a full time career in software engineering leadership. I recently completed a Master of Science in Applied Artificial Intelligence at the University of San Diego. I've got a background in technology and a few other degrees that have shaped how I think about technical and ethical problems in the world today.

• M.S. in Applied Artificial Intelligence (University of San Diego) — Alcalá 100 Honoree
• M.A. in Religion with a focus on Church History & Theology (Trinity Episcopal)
• B.A. in History (Hillsdale College)

I am a Vice President of Engineering at Rocket, based in Detroit, Michigan, where I lead the engineering teams behind our digital client experiences — from the first unauthenticated visit through qualification, application, and mortgage origination. My teams ship web and AI/chat products at scale, powered by cloud infrastructure on AWS, with a focus on continuous delivery, reliability, and engineering excellence. I'm deeply invested in advancing agentic engineering workflows — building a culture where AI is a first-class partner in how we design, write, and ship software.

• 🧑‍💻 Multi-Disease Outbreak Forecasting with Temporal Deep Learning (M.S. Capstone)

  • Goal: Build a temporal deep learning system to forecast multiple infectious disease outbreaks using Canadian public health surveillance data.
  • Tech Stack: Python, Jupyter Notebook, LSTM, Transformer, ARIMA, Pandas, NumPy, Matplotlib
  • Outcome: Developed and evaluated multiple forecasting models across diseases including influenza and whooping cough, with geographic gap analysis validating model performance against PHAC reporting patterns.
  • GitHub Repository

• 🧑‍💻 Cloud Resume Challenge

  • Goal: Build and deploy a simple HTML/CSS website with cloud resources and IAC.
  • Tech Stack: Lambda, DynamoDB, S3, CloudFront, Route53, and API Gateway.
  • Outcome: Learned and demonstrated execution in a handful of AWS services, as well Hashicorp's Cloud Platform and GitHub Actions workflows.
  • GitHub Front End GitHub Back End

• 🧑‍💻 VenueSignal

  • Goal: Build, train, and deploy a fully-operational MLOps system. The model was trained on the Yelp Open Dataset to predict the impact of parking accessibility on new businesses in urban settings.
  • Tech Stack: Python, SageMaker, Xgboost, S3, Athena, CloudWatch.
  • Outcome: Feature store with 36 features deploys a robust model that includes model drift improvements based on real time monitoring and drift feedback.
  • GitHub Repository

• 🧑‍💻 Computer Vision for Reptile Detection

  • Goal: Build and Train a model to detect different species of reptiles in images
  • Tech Stack: Python, PyTortch & Ultralytics YOLOv10, BioTrove-CLIP, Numpy, ImageHash, OpenCV
  • Outcome: Model can match to 60% accuracy some 531 reptile species found in the BioTrove dataset.
  • GitHub Repository

• 🧑‍💻 Intelligent Investment Research Agent

  • Goal: Implement an agentic workflow with prompt chaining to deliver a self-improving financial news agent.
  • Tech Stack: Python, LangChain, LangGraph, OpenAI
  • Outcome: Agent can retrieve news and stock price information about publicly traded comapnies, including providing sentiment analysis of news coverage and stock price trends.
  • GitHub Repository

• 🧑‍💻 MIDI Detection System for Identifying Classical Music Composers from Sound Bites

  • Goal: Implement LSTM and CNN against a Kaggle MIDI dataset to correctly identify four major classical composers
  • Tech Stack: Python, CNN, LSTM
  • Outcome: models performed reasonably well for the example, but real advancements are needed to detect more composers at scale.
  • GitHub Repository

• 🧑‍💻 Forcasting the Unemployment Rate for the San Diego Metropolitan Statistical Area

  • Goal: Implement a model leveraging Bureau of Labor Statistics Unemployment Data to forecast future unemployment rates.
  • Tech Stack: Python, numpy, Pandas, ARIMA, DeepAR
  • Outcome: DeepAR model outperformed other models, but isn't necessarily the best use case for it. Additional economic and geopolitical factors are likely needed to effectively build out a production-grade model.
  • GitHub Repository

• 🧑‍💻 Smart Home Energy Consumption Anomaly Detection and Forecasting

  • Goal: Design an IoT system that can detect energy consumption anomalies in a smart home.
  • Tech Stack: Python, Jupyter Notebook, Keras (Tensorflow)
  • Outcome: Deep learning autoencoder was used for anomaly detection, and an LSTM model was used to predict future energy consumption with 99.84% accuracy in its predictive trends across seven days.
  • GitHub Repository

• 🧑‍💻 Predicting Emotion From Speech With A Speech Emotion Recognition (SER) Model

  • Goal: Identify and implement a model to detect emotional states in speech.
  • Tech Stack: Python, Jupyter Notebook, scikit-learn, librosa, TensorFlow
  • Outcome: HuBERT Enhanced and CNN-LSTM Enhanced models both produced greater than 90% accuracy, with CNN-LSTM Enhanced achieving an accuracy rate of 98%.
  • GitHub Repository

• 🧑‍💻 Predicting Obesity: How Lifestyle and Dietary Factors Shape Weight Outcomes

  • Goal: Identify and implement a model to aid early-detection models for obesity.
  • Tech Stack: Python, Jupyter Notebook, scikit-learn, numpy, Pandas
  • Outcome: Random Forest Modeling was trained and evaluated against the dataset and found to be the most predictive, at effectively 94% accuracy, of detecting correlative effects of obesity.
  • GitHub Repository

• 📝 Towards a Christian Ethical Framework for Artificial Intelligence

  • 2019 (unpublished)
  • Capstone Research Project for Master of Arts in Religion (Church History & Theology).
  • Focused on how a Christian ethical understanding of humanity might inform a perspective on artificial intelligence. This project looked specifically at the lens of how evangelical theology has a very narrow perspective on human identity and, as a result, cannot speak effectively in response to artificial intelligence.

📫 Reach me via email or on LinkedIn if that's your preference.