I am a machine learning researcher and senior data scientist with experience in graph neural networks, medical imaging, computer vision, uncertainty quantification, probabilistic modeling, LLM systems, and production ML infrastructure.
My current doctoral work at The University of Texas Rio Grande Valley includes longitudinal breast DCE-MRI forecasting, tumor-graph deep learning, stochastic digital twins, and automated registration of sequential fluorescence images.
Current doctoral research
I am pursuing a PhD in Computer Science with Interdisciplinary Applications at The University of Texas Rio Grande Valley, where I conduct research in the Machine Intelligence Lab. My work focuses on graph neural networks, uncertainty quantification, probabilistic modeling, and medical imaging.
I develop models that forecast breast-cancer response from longitudinal dynamic contrast-enhanced MRI while preserving regional tumor structure and producing calibrated patient-level uncertainty estimates. My current work includes endpoint-calibrated graph rollouts, image-embedding tumor graphs, conformal prediction, and stochastic reaction-diffusion models with sequential Bayesian calibration.
I also designed and implemented an automated, optimization-based 2D registration pipeline for sequential fluorescence images of *Tribolium* embryos. The system derives structural masks from DAPI channels, estimates translation, scale, and rotation through a similarity transform, applies the transformation consistently to gene-expression channels, and evaluates alignment through mask overlap and visual overlays.
Industry experience
From 2022 through September 2026, I worked at Gray Falkon LLC, first as a developer and later as a senior data scientist. I designed and scaled production systems involving computer vision, LLM-enabled messaging, data collection, automation, secure browser infrastructure, microservices, and operational monitoring. My work included image-infringement detection across large e-commerce datasets, classification and analysis services, internal access tooling, and alerting systems.
Earlier, as an associate software engineer at Imagine Learning, I developed software and machine-learning products for educational technology. I implemented an early model for evaluating free-response student text, developed interactive literacy tools in Unity, and built REST APIs for educator-facing analytics and reporting.
Earlier research
At Northeastern University, I worked in the Bayesian and Machine Learning Lab on probabilistic programming, nested inference, theory-of-mind reasoning, and autonomous agents. This work produced *Nested Reasoning About Autonomous Agents Using Probabilistic Programs*, presented at two ICML 2019 workshops.
During my master’s studies at Brigham Young University, I developed probabilistic-programming methods for autonomous decision-making and completed the thesis *Probabilistic Programming for Theory of Mind for Autonomous Decision Making*. I also contributed to research in recommendation systems and data mining.
As a visiting student with the MIT Probabilistic Computing Project, I worked on generative models, goal inference, custom inference proposals, and visualization tools for probabilistic programs.
Education
– PhD, Computer Science with Interdisciplinary Applications, The University of Texas Rio Grande Valley — in progress
– Doctoral studies in Computer Science, Northeastern University
– MS, Computer Science, Brigham Young University
– Visiting Student, MIT Probabilistic Computing Project
– BS, Computer Science, Brigham Young University
