Research
My instrumentation work sits at the intersection of wireless and optical sensing, physical-layer and distributed systems, and applied ML. Below is a partial record of past projects, publications, and coursework.
Research Projects
-
Jump 2.0 — California Planet Search Data PlatformArchitected and led development of a production distributed data science platform for the California Planet Search, designed to accelerate analysis of the precision radial-velocity datasets produced by instruments including the Keck Planet Finder.
-
Deep Learning for PANOSETIDesigned and implemented the first deep-learning pipeline for the PANOSETI collaboration, achieving 95% classification accuracy and 0.97 average precision in automated interference detection for daily terabyte-scale datasets of wide-field, 20 μs-integration optical/near-IR images.
-
High-Speed Data Acquisition SystemDeveloped and maintained an ultra-high data-rate (100k frames/sec) C++ acquisition pipeline, integrating an asynchronous gRPC API for real-time analysis and robotic telescope control, leading several extensibility-focused refactors, and establishing a self-hosted hardware-software GitHub Actions CI pipeline to validate fault-tolerance and >99.99% data integrity. This work carried PANOSETI from a 3-telescope prototype at Lick Observatory to a 4+ telescope production deployment at Palomar Observatory.
-
Terabyte-Scale Data PipelineCo-designed and implemented a scalable data-reduction pipeline (Zarr, Ray, Nextflow) for terabyte-scale datasets and real-time classification, leading technical prototyping from a self-administered 4-GPU cluster to San Diego Supercomputer Center facilities.
-
Unsupervised Anomaly DetectionProposed and prototyped an unsupervised anomaly detector using a β-Variational Autoencoder, capable of clustering Cherenkov events, noise, and stellar signals based on low-dimensional latent embeddings.
-
Characterizing Polar ExpressEmpirically characterized the Polar Express Muon variant, evaluating its sensitivity to key hyperparameters and the extent to which it stabilizes the attention mechanism in Transformer architectures.
Publications & Presentations
-
Nanosecond differential timing using inexpensive differential GNSS receivers
-
Machine learning applications for anomaly and interference detection on PANOSETI data
-
Identifying clouds in panoramic SETI data with machine learning
Education
Massachusetts Institute of Technology
Sept 2026 – present
Ph.D. in Electrical Engineering and Computer Science
University of California, Berkeley
Aug 2021 – Dec 2025
Bachelor of Arts in Applied Mathematics and Computer Science (double major) · GPA: 3.88
Class projects and independent work (CS180, EECS151 CPU design) are on the Projects page.