Biography

I am a computational scientist who builds software solutions for cutting-edge defense applications. Experience with modern software engineering combined with a deep background in scientific modeling and machine learning enables me to deliver scalable production systems with leadership-class advanced capability. Seeing my team succeed and our products have an impact is hugely rewarding. To that end, I drive project success in whatever role I am most needed, from client interaction and outreach to architecture and technical development.

I work at Booz Allen Hamilton as a senior software engineer. I changed tracks after almost five years at Sandia National Laboratories. At Sandia, I performed fundamental research at the intersection of machine learning and mathematical modeling, and contributed to the nuclear deterrence mission by leveraging my math background. I was fortunate to start my career as a John von Neumann postdoctoral fellow in computational science at the Albuquerque, NM site before joining the department of Quantitative Modeling and Software Engineering in Livermore, CA as staff. See my Publications page for more details.

Though I have to turn down research engagements to focus on my new career, I'm happy to stay in touch with my research colleagues. I enjoy discussing ideas and consulting on technical approaches. I am available on LinkedIn for those who want to reach out.

News & Featured Publications

• The New York Times published an article titled "The U.S. Is Building an Early Warning System to Detect Geoengineering" that featured work done with my former colleagues at Sandia. Under the CLDERA project, I developed AI-accelerated reduced order models for climate dynamics. As the article describes, those surrogate models allowed us to efficiently solve source identification problems in messy, data-sparse situations. The NYT article links to our preprint, which is currently under peer review.
  
  
• A survey of constrained Gaussian process regression: approaches and implementation challenges is one of the most highly cited articles in the Journal of Machine Learning for Modeling and Computing!