John Abrahams
johnnycabrahams@gmail.com | github | linkedin | resume
| Now | Penn MS Data Science (GPA 3.62) |
|---|---|
| Prev | SWE intern at Ninth Wave (summer 2026) Kronos paper (2025) NYBSS therapy chatbot (2025-2026) BSCS Lehigh 2025 (GPA 3.65, major 3.75), Dean's list 4 semesters |
| Languages | Python, Rust, Go, Java, C++, C, WebAssembly |
| Machine Learning | PyTorch, Reinforcement Learning, GRU/sequence models, LLMs, NLP |
| Systems | AWS, FastAPI, Spring Boot, embedded/ESP32, multithreading, concurrency |
| Data | probability & statistics, regression, SVM, EM algorithm |
Featured projects
Kronos: A Type II Exovisor with WebAssembly
2025. Rust. Co-authored paper.
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 (3x denser than Wasmtime); up to 6.7x speedup on dense matmul while preserving per-tenant trap containment.
DJ Reinforcement Learning System
Dec 2025. Embedded. GRU + RL.
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.
Other projects
Ninth Wave: Software Engineer Intern
Summer 2026. Fintech. Java/Spring, AWS, Python LLM tooling.
Summer 2026 SWE internship at an open-finance fintech. Built Python LLM tooling for bank-API-to-canonical-model mapping and automated RFP generation across ERP integrations (Xero, NetSuite, QuickBooks), and contributed to a Java/Spring Boot developer portal and an AWS Bedrock onboarding agent (Secrets Manager, OpenSearch).
Systematic Trading Bot
2026. Python, Alpaca, AWS, backtesting.
A systematic daily-rebalance U.S. ETF momentum strategy on the Alpaca API, validated through a vectorbt backtesting harness. Runs unattended live paper trading on AWS EC2 with Secrets Manager and systemd timers.
neurovariety: Open-Source ML Library
2026. Rust + Python. Algebraic geometry. MIT license.
An open-source Python/Rust library that models neural-network function spaces as algebraic varieties, computing dimension, degree, and singular loci to quantify expressivity and implicit bias. Performance-critical core in Rust behind a Python API, MIT-licensed with CI.
Tracklist Engine
2026. Audio ML. PyTorch, DETR, Demucs, MERT.
A multi-stage audio-ML pipeline (scrape, ingest, analysis, labeling, alignment) that reconstructs how recorded DJ mixes are built from their source tracks. Combines DETR cue-point detection, Demucs source separation, and MERT music-transformer embeddings over a normalized SQLite schema.
Clinical Therapy Chatbot
May 2025 to Mar 2026. LLaMA, FastAPI.
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
2024. Co-founded. React + Python + AWS.
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
2024. Capstone. NLP + AWS.
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.
Hangover Simulator
Interactive. ODE model.
BAC kinetics, acetaldehyde clearance, sleep disruption, and an RL discount factor for drunk-you's choices.
Education
University of Pennsylvania, School of Engineering and Applied Science, December 2026
M.S.E. in Data Science. GPA 3.62.
Coursework: Probability Theory (Ph.D. course), Advanced Topics in Operating Systems, Advanced Topics in Computer Architecture, Big Data Analytics, Theoretical & Computational Neuroscience, Smart Devices
Lehigh University, P.C. Rossin College of Engineering and Applied Science, May 2025
B.S. Computer Science & Engineering. GPA 3.65 (Major 3.75). Minor: Probability & Statistics. Dean's List Spring 2023 – Spring 2025.
Coursework: Applied Machine Learning, Blockchain and Database Systems
Experience
New York Brain & Spine Surgery, Software Engineer. May 2025 – March 2026
- Built a production therapy chatbot on LLaMA and FastAPI, blending rule-based clinical workflows with LLM-generated responses.
- Designed a configurable multi-agent architecture supporting multiple mental-health conditions and rapid prompt iteration.
- Developed backend APIs and state management powering safe, real-time conversational flows and fast end-to-end iteration.
Ninth Wave, Software Engineer Intern, Compass (open-finance AI onboarding). May 2026 – Aug 2026
- Researching a two-model code-generation system for Compass, Ninth Wave's open-finance onboarding agent: an HRM-Text recursive executive that plans and writes structured outputs over a MeMo parametric memory trained on internal documentation, replacing RAG and prompt engineering with learned memory.
- Contributed to Flight-Deck (Java/Spring Boot developer portal) and the Compass agent on Amazon Bedrock AgentCore, working across AWS (Secrets Manager, OpenSearch, Bedrock).
- Built Python LLM tooling for bank-API-to-canonical-model mapping and automated RFP response generation across ERP integrations (Xero, NetSuite, QuickBooks).
Kronos: Multi-Tenant WebAssembly Runtime, UPenn Research (Prof. Sebastian Angel). Oct 2024 – Present
- Built Kronos, a multi-tenant WebAssembly runtime in Rust (~5K lines) that packs tenants ~20× denser than Docker (~0.08 MiB per isolate) using exokernel-style capability gating with per-invocation fuel and wall-clock budgets.
- Engineered a work-stealing thread pool that dispatches guest pthread_create calls for shared-memory data parallelism, reaching 6.7× speedup on four cores.
- Exposed a tiered ~74-entry capability-gated host interface; benchmarked against the wasmtime and wazero runtimes on C++ kernels (matmul, k-means, SVD) and co-authored a 9-page systems paper introducing the resulting 'Type II exovisor' abstraction.
The Quant Game, Co-Founder. May 2024 – Aug 2024
- Co-founded and built a full-stack options-strategy simulator (React, Python) delivering real-time backtests and performance metrics.
- Architected an AWS data layer storing and serving 61M+ financial data points at high availability.
Systematic Trading Bot, Independent. Apr 2026 – Present
- Built a systematic daily-rebalance U.S. ETF momentum strategy on the Alpaca API, validated through a vectorbt backtesting harness.
- Automated live paper trading on AWS EC2 with Secrets Manager and systemd timers for unattended daily execution.
Capstone Document Search System, Senior Capstone, Lehigh University. May 2024 – July 2025
- Engineered a full-stack search engine over 23,000+ Dropbox documents on AWS for fast, sentence-level content retrieval.
- Built an NLP indexing pipeline that parses heterogeneous file types and segments content at the sentence level for granular highlight extraction.
Writing
Kronos: A Type II Exovisor Architecture with WebAssembly (2025, with Ajax Li)
Predictive Outcome Modeling After ACDF (LDR-C ROI Implant) (2024, co-author, 236-patient cohort study)
Gradient Descent Analysis (2023, with Prof. Arielle Carr, Lehigh)
A Highlighting Algorithm for Document Search (2024, capstone writeup)
More on the writing page.