I study computer science at Michigan and like building things people actually use. Right now that means cardiac ML research at Michigan Medicine and a sales platform three businesses run on.
I build things people use.
a sales platform, $500K+ through itI look for patterns in heartbeats.
cardiac ML at Michigan MedicineI make systems that don’t fall over.
Go, replication, MapReduceMatched 18,000+ ECGs to echocardiograms for 5,400 patients with left bundle branch block. Broke every waveform into Haar wavelets on the university’s SLURM cluster and found 2-millisecond bins in lead aVF that separate heart failure patients from everyone else.
Linked 1.9 million ECGs with 303,000 echocardiograms, narrowed them to a 592-patient cohort in SQL, and trained an XGBoost model that predicts who responds to cardiac resynchronization therapy (0.71 ROC-AUC, pre-op data only). It won a Blue Ribbon at the spring symposium.
Fixed bugs in a webhook delivery system on AWS Lambda and shipped a new function through GitHub Actions.
Built them a sales platform in Next.js and Supabase and wired it to Zoho Inventory, so 6,000+ products stayed in sync and nobody typed invoices by hand anymore (60% less of that work). I kept the code. It turned into the platform below.
Led architecture on team projects, built a digital art gallery app, and helped newer developers get comfortable with Swift.
Three businesses take their orders through it, and $500K+ has gone through so far. Most of the real work is keeping every business in sync with Zoho without getting throttled: incremental, batched syncs on a staggered schedule, plus exponential backoff with jitter when the API pushes back.
Primary/backup replication in Go. A view service promotes the backup when the primary goes quiet and never lets two primaries exist, even across a network partition. The catch: no mutexes allowed, only goroutines and unbuffered channels.
Time-series vitals and labs for 16,000+ patients, an RBF-kernel SVM weighted for the class imbalance, and a lot of cross-validation on C and γ. It landed at 0.86 AUROC (bootstrapped CI 0.81–0.91).
First the MapReduce framework: a manager, workers, and UDP heartbeats to notice when one dies. Then I used it to index 100,000+ web pages, ranked with tf-idf mixed with PageRank.
Python for anything with data, and C++ when I want to know exactly what the machine is doing. Plus SQL, PyTorch, scikit-learn, XGBoost, Postgres, AWS Lambda, and a SLURM queue I know too well. Lately I love exploring what Claude can do. Claude Code is part of how I work, mostly on the platform and front-end work like this site.