In Spring 2022, I earned my Bachelor of Science in Applied Mathematics with a minor in Computer Science at UTRGV, graduating Summa Cum Laude with the Highest Distinction in Honors Studies. The following fall, I began pursuing my PhD in Mathematics and Statistics with Interdisciplinary Applications, working at the UTRGV Institute for Advanced Manufacturing (IAM). My dissertation focuses on developing data-driven methods to efficiently navigate complex parameter spaces in materials science and manufacturing engineering. I leverage neural networks and machine learning algorithms to accelerate materials design and optimize engineering processes, towards the aim of expanding the field of AI for scientific discovery.
Through my work with the IAM, I have gained valuable hands-on experience collaborating with Department of Energy (DOE) national laboratories, such as Oak Ridge, Argonne, and Lawrence Livermore. I dream of giving back the mentorship graciously given to me throughout my journey. Currently, I'm seeking a full-time, post-grad position where I can work out of Edinburg, Texas.
My experiences at DOE labs have afforded me the opportunity to contribute to projects in high-performance computing (HPC) and autonomous experimentation (AE) applying advanced AI methods to real-world manufacturing challenges. Thanks to the National Nuclear Security Administration (NNSA) MSIIP program, I have been able to collaborate year-round with LLNL since Summer 2024. First, I joined the Applied Statistics Group at Lawrence Livermore National Lab, building neural network architecture (optimized on state-of-the-art HPC systems) that can generate equation-of-state tables and predict phase maps with an overall accuracy of ~97%.
In October 2024, I joined the Analytics for Advanced Manufacturing group at LLNL to develop scalable, intelligent automation systems. Through my involvement, I gained hands-on experience with cutting-edge robotics & AI integration as part of an exceptional interdisciplinary team. Our machine learning models consistently achieved high performance, both in recognizing spoken sentences like "pick up the vial", and with visually detecting abnormalities in a given scene. We developed domain-agnostic workflows to empower subject matter experts with limited coding experience to harness advanced predictive models for their research needs.
Post-grad, I want to keep building AI systems on a team dedicated to advancing scientific discovery.