Hello! I'm Lawrence.

Dec 2025 — Present

Research Software Engineer

Princeton University · Princeton, NJ

Research software engineer at the AI Lab at Princeton University.

Jul 2023 — Jul 2025

Postdoctoral Fellow

Thomas Jefferson National Accelerator Facility (JLab) · Newport News, VA

Developed non-parametric statistical frameworks and end-to-end analysis pipelines for hadron physics using Python, JAX, and OpenMPI.

• iftpwa GitHub →

  Dec 2023 — Jul 2025

  Developing a declarative framework for smooth non-parametric statistical models using Python, JAX, and OpenMPI with Gaussian Processes and Variational Inference, enabling Bayesian inference over O(10^6) free parameters.

  python jax openmpi gaussian-processes variational-inference information-theory
• PyAmpTools GitHub →

  Jul 2023 — Oct 2025

  Built an end-to-end analysis pipeline generating physics events from a model, emulating detector efficiency via normalizing flows, and interfacing with both Bayesian- and frequentist-based optimization frameworks for rapid closure tests. Contains Python bindings for the collaboration's C++ analysis software and maintains user-facing documentation to ensure long-term sustainability.

  python c++ normalizing-flows bayesian-inference

Aug 2016 — May 2023

PhD Research Assistant

Florida State University · Tallahassee, FL

Published research in top physics journals applying deep learning and Bayesian methods to hadron spectroscopy and supernova cosmology. Applied maximum likelihood optimization, Markov Chain Monte Carlo, and model selection methods to complex real-world physics problems.

• Supernova Spectral Templates using conditional VAEs

  Jan 2023 — May 2023

  Published in The Astrophysical Journal: Collaborated with observational astronomers to develop a conditional variational autoencoder for generating template supernova spectra, reducing a class of systematic uncertainties by ~90%.

  python pytorch vaes bayesian-inference
• Q-Factors Background Subtraction GitHub →

  May 2021 — Aug 2022

  Implemented a computationally intensive background subtraction technique in C++ with multiprocessing support, improving analysis efficiency for large datasets.

  c++ multiprocessing
• Deep Learning Exotic Hadrons

  Jan 2021 — Oct 2021

  Published in Physical Review D: Developed a framework using Deep Neural Networks to determine the nature of exotic hadrons from their spectra, utilizing Shapley values to understand feature importance.

  python pytorch deep-learning shapley-values