John Abrahams
Computer Science & Data Science.
Currently a master’s student in Data Science at the University of Pennsylvania, and co-author of Khronos, a multi-tenant WebAssembly runtime. Before Penn — BS in Computer Science & Engineering at Lehigh, parallel WebAssembly with Prof. Spear, a clinical therapy chatbot at New York Brain & Spine Surgery (through March 2026), and a fintech sim with 61M data points.
Two larger things.
Khronos — A Type II Exovisor with WebAssembly
A multi-tenant runtime that combines WebAssembly's sandbox with exokernel-style capability gating and a custom wasi:thread-spawn dispatcher. ~5,000 lines of Rust; ~0.08 MiB per isolate (3× denser than Wasmtime); up to 6.7× speedup on dense matmul while preserving per-tenant trap containment.
DJ Reinforcement Learning System
A wireless ESP32-S2 sensor mesh — environmental, audio, thermal — that streams crowd-engagement metrics to a Raspberry Pi controller. A 2M-parameter GRU pretrained on ~3,000 DJ sets predicts the next song; an RL head adapts to live sensor feedback. Built with Chris Spletzer for UPenn ESE 519.
Smaller things.
Clinical Therapy Chatbot
A production therapy chatbot for New York Brain & Spine Surgery, blending rule-based clinical workflows with LLM-generated responses. Configurable multi-agent system spanning multiple mental-health conditions.
The Quant Game
A full-stack options-trading sim with 61M financial data points on AWS. Users build and backtest strategies and watch them play out against historical market data.
Dropbox Document Search Engine
A search engine for ~23,000 Dropbox documents, with sentence-level highlight extraction. Partitioned indexing + Dropbox API integration for real-time access. Lehigh capstone for an early-stage startup.
Selected papers.
- Khronos: A Type II Exovisor Architecture with WebAssembly
- Predictive Outcome Modeling After ACDF (LDR-C ROI Implant)
- Gradient Descent Analysis
- A Highlighting Algorithm for Document Search
Full list and reading notes on the writing page.