Presented at the 2026 Argonne Postdoctoral Research and Career Symposium
Presented research at Argonne National Laboratory's 2026 Postdoctoral Research and Career Symposium.
Research log
News & milestones
Presentations, publications, teaching, recognition, and career updates, newest first.
ParslBox presented at the APeX Summit
Delivered an oral presentation on ParslBox as a computational materials workflow executor for artificial intelligence agents on high-performance computing systems. Watch the talk
Attended the GRC at Newry, Maine on Computational Materials Science and Engineering
Presented automated and agentic machine-learned interatomic potential development using ParslBox at the 2026 Gordon Research Conference on Computational Materials Science and Engineering.
Mentored at the Intro to HPC Undergraduate Bootcamp
Co-led a molecular-property prediction project for undergraduate students and delivered a hands-on introduction to parallelization.
Argonne Research Slam campus finalist
Selected as a campus finalist in Argonne National Laboratory's 2026 Research Slam.
Supported the Argonne Open House
Led tours of the Aurora supercomputer, managed a color-matching activity for children, and assisted visitors during Argonne's 2026 Open House.
ParslBox paper accepted at AgenticAI4HPC
The ParslBox paper was accepted at AgenticAI4HPC 2026, an SC'26 Workshop. Citation
Multi-agent workflow paper accepted at ISC-HPC
The paper on multi-agent orchestration for high-throughput materials screening on a leadership-class system was accepted at ISC-HPC'26. Citation
Molten FeCl₂ and FeCl₃ study published
The structure study combining high-energy X-ray diffraction, an empirical potential, and MLIPs was published in ACS Materials Au. DOI
Molten iron chlorides poster at MRS
Presented work on FeCl₂ and FeCl₃ structure using high-energy X-ray diffraction and machine-learned interatomic potentials at the 2026 MRS Spring Meeting.
Invited MDPI webinar presentation
Presented MACE foundation MLIPs, their performance, applications, and fine-tuning in the webinar "Energy and Advanced Computing in the Age of Machine Learning: From Quantum to Grid."
Redox-potential graph-neural-network study published
The study combining density functional theory and graph neural networks for Fe(II)/Fe(III) redox-potential prediction was published in Digital Discovery. DOI
Redox graph-neural-network work presented at ECS
Delivered an oral presentation on graph neural network approaches for predicting redox potentials of transition-metal complexes at the 248th ECS Meeting.
Completed ATPESC
Participated in the Argonne Training Program on Extreme-Scale Computing.
Argonne seed funding as co-PI
Secured $50k in Argonne Laboratory Directed Research and Development seed funding as co-PI to develop vision-language models for cyclic-voltammetry analysis.
Joined Argonne National Laboratory
Joined the Computational Science Division as a postdoctoral researcher.
Completed Ph.D. at UC Merced
Earned a Ph.D. in mechanical engineering after research on shear-driven mechanochemistry and tribology.
