CV

Graduate Research Assistant

Caltech High Energy Physics Group

Research at the CMS experiment at CERN and on deep learning methods for physics

• Lead RINO, a self-supervised learning approach and a step towards foundation models for jets, with a spotlight paper at the ML4PS workshop at NeurIPS 2025
• One of the main contributors to the boosted Higgs boson pair search in the four bottom quark final state, responsible for the trigger and jet tagger calibrations behind the published results and for BDT trainings, datacard creation, and final fits in the continuing analysis

Visitor

Fermi National Accelerator Laboratory

Self-supervised learning methods for high energy physics and the search for Higgs boson pair production with CMS data

Undergraduate Researcher

Duarte Lab

Geometric deep learning for experimental high energy physics

• First-authored the Lorentz Group Equivariant Autoencoder (LGAE), an autoencoder fully equivariant to the Lorentz group
• Developed a ParticleNet-based tagger for boosted Higgs boson decays to W boson pairs for the CMS experiment, responsible for model training on Kubernetes clusters

Ph.D. Candidate

California Institute of Technology

Physics

• Master of Science in Physics received June 2026
• Advised by Prof. Maria Spiropulu
• Research in machine learning and experimental high energy physics

Bachelor of Science

University of California, San Diego

Physics and Computer Science (double major)

• Phi Beta Kappa
• Dean’s Undergraduate Award for Excellence

Undergraduate study

University of California, Santa Barbara

Physics

Teaching Assistant

Caltech Ph 22 (Computational Physics Laboratory III)

One of two TAs who designed and built the course’s final project on reinforcement learning for quantum state preparation

• Led weekly lab sessions and taught core AI concepts, from neural network training to policy gradient methods
• Built the final project’s Gymnasium environment over a Tavis-Cummings cavity QED simulator, the REINFORCE reference implementation, and PPO, SAC, and TQC baselines with MLP, LSTM, and Transformer policies
• Designed the project questions, the graded ladder of target quantum states, reward shaping, and multi-seed evaluation requirements
• Graded coursework and mentored students through their final project implementations

Spotlight paper (first author) at the ML4PS workshop at NeurIPS 2025

ML4PS workshop at NeurIPS

Offered to about 1% of the workshop’s accepted papers

Fermilab LPC Guest and Visitor Award

Fermilab LHC Physics Center

Fermilab LPC Guest and Visitor Award

Fermilab LHC Physics Center

Phi Beta Kappa Honor Society

Phi Beta Kappa

Dean's Undergraduate Award for Excellence

UC San Diego Physical Sciences

Undergraduate Summer Research Award

UC San Diego