Education

1. Ph.D. in Biostatistics · University of Southern California

   August 2022 – January 2027 (expected)

2. M.Sc. in Biostatistics · New York University

   September 2020 – May 2022

3. B.A. in Statistics and Chemistry · University of California, Santa Barbara

   September 2015 – December 2019

Experience

1. Computational Biology Intern · Cellanome

   June 2026 – August 2026 · San Diego, CA

   • Analyzed multimodal single-cell datasets generated on the R3200 platform with CellCage technology across diverse experimental settings, using rigorous, streamlined, and reproducible workflows.
   • Developed a deep-learning trajectory-modeling framework and supporting internal software for longitudinal live-cell imaging, capturing cellular morphodynamic patterns and revealing biological cell states beyond snapshot morphology or endpoint transcriptomics alone.
   • Applied visualization tools, integrative morphodynamic–transcriptomic analyses, and pathway enrichment to characterize dynamic cell states and their associated transcriptomic profiles.

2. Graduate Research Assistant, Biostatistics · USC Department of Population and Public Health Sciences

   August 2022 – present · Los Angeles, CA

   • Engineered LUCID, a statistical quasi-mediation framework and R package for multi-omics clustering and inference with high-dimensional exposures and outcomes — rewritten for a 120× speedup and extended with variable selection, uncertainty quantification, missing-data handling, flexible integration strategies, and visualization.
   • Developed Praxis-BGM, a scalable Bayesian transfer-learning framework for Gaussian mixture models leveraging natural-gradient variational inference and informative biological priors to improve stability, accuracy, and interpretability in high-dimensional, small-sample omics, with applications to TCGA and METABRIC data (Bioinformatics, 2026).
   • Implemented computational tools and pipelines for multimodal data integration, label transfer, and biological discovery with AIMS@USC, extended to single-cell and spatial transcriptomics (e.g. Xenium).
   • Collaborated with interdisciplinary teams across epidemiology, environmental health, and computational biology, providing statistical consulting on studies of environmental exposures such as PFAS and their multi-omics-mediated health outcomes.

3. Graduate Research Assistant · New York University

   February 2021 – September 2022 · New York, NY

   • Conducted biostatistics and deep learning research in 3D medical imaging, adversarial robustness, and neuroimaging inference.
   • Designed BiTr-UNet, a CNN–Transformer architecture for 3D brain tumor segmentation, presented at the MICCAI BrainLes workshop.
   • Co-developed scalable Hidden Markov Random Field (HMRF)- and deep-learning-based spatial multiple-testing frameworks — including DeepFDR — for inference across hundreds of thousands of FDG-PET voxels, improving power while controlling false discovery rate.

Skills

Download full resume (PDF) →