Maxwell Vaglica
Data & AI/ML Engineer at Tempus AI, building production agentic-AI systems, full-stack apps (React + FastAPI on GKE), and data pipelines used daily by 100+ scientists. M.S. in Computer Science from Georgia Tech, Computing Systems specialization.
iOS Apps
Native iOS applications built with Swift and SwiftUI
TabGuard
Popup & Tab Blocker
Block annoying popups and unwanted new tabs in Safari. Features Smart Mode that allows your clicks while blocking script-triggered popups, site rules, and block history.
PhotoScan
QR & Barcode Reader
Scan QR codes and barcodes from any image in your photo library — no live camera needed. Features batch scanning, 20+ barcode types, scan history, and data export.
Real models. Real math. In your browser.
Two of the projects below ship with interactive sandboxes that run entirely client-side — no server, no API call.
Trained PyTorch NN, running as JS matmul
Slide the load and generation parameters of a 39-bus IEEE power system, watch the model predict overloads across all 46 branches in real time. Weights extracted from the trained model.pth and run as pure JavaScript — no model server, no library download.
Encrypt + decrypt with BigInt RSA
Type any message, watch it round-trip through textbook RSA in three columns: plaintext bytes, ciphertext numbers, and the decrypted result. All native JavaScript BigInt math — zero external libraries.
Project Spotlight
Graduate studies at Georgia Tech and personal research work
LeetCode Problem Solutions
Collection of algorithmic coding challenges solved in Python and C++, covering data structures, string manipulation, and SQL/Pandas data analysis across easy to hard difficulty levels.
DeepLabCut: Rat Behavior Analysis
Deep learning pipeline using DeepLabCut to track rat body parts and detect rearing behavior from video data, achieving high accuracy after 350,000+ training iterations.
Sea Hero Quest: Clinical Data Analysis
Large-scale data analysis of 4+ million players' spatial navigation patterns to identify cognitive biomarkers for dementia research, processing 78,000+ complete game sessions.
Cryptography: RSA & Vigenere Cipher
Full implementation of RSA encryption/decryption with cryptographic attacks including weak key detection, broadcast attacks using Chinese Remainder Theorem, and parity oracle exploits.
BGP Hijacking Simulation
Network security simulation demonstrating BGP route hijacking attacks in Mininet, implementing multi-router topologies with Quagga/Zebra and real-time attack visualization.
Trading Strategy Evaluation
ML-based trading system using ensemble methods (BagLearner with Random Trees) to predict stock movements, with full backtesting simulation including transaction costs.
BGP Measurements & Analysis
Large-scale network analysis processing BGP routing data to track internet routing dynamics, autonomous system growth, and prefix advertisement patterns using pybgpstream.
SDN Firewall Implementation
Software-Defined Networking firewall using POX controller and OpenFlow protocol for dynamic packet filtering with programmable security policies.
Machine Learning for Cyber Security
End-to-end ML pipeline for security threat detection including data preprocessing, feature engineering, model training, and evaluation on real-world security datasets.
API Security & Penetration Testing
Hands-on security assessment identifying and exploiting API vulnerabilities including authentication bypasses, injection flaws, and authorization issues.
Web Security Assessment
Comprehensive web application penetration testing covering SQL injection, XSS, CSRF, and authentication bypass with detailed vulnerability analysis.
Q-Learner: Reinforcement Learning Trading
Reinforcement learning implementation using Q-learning and Dyna-Q for automated trading strategy development with experience replay and model-based planning.
Technical Indicator Evaluation
Quantitative finance project implementing technical indicators (SMA, Bollinger Bands, RSI, MACD) and developing theoretically optimal trading strategies.
Power System Neural Network
Deep learning model using PyTorch to predict branch overloads in electric power grids, implementing neural networks for critical infrastructure monitoring.
JobCompare 6300: Android Team Project
Four-person Android app (Java, Gradle, API 34) built for Georgia Tech CS 6300 Software Development Process — full SDLC artifacts including design docs, UML class diagrams, use case models, and a written test plan.
PLC Programming & Industrial Automation
Industrial control system programming using IEC 61131-3 Structured Text for automated positioning systems with real-time control logic.
Experience & Education
4+ years of professional experience building production data pipelines, cloud applications, and AI/ML systems serving 100+ users across multiple laboratories. Backed by an M.S. in Computer Science from Georgia Tech with a Computing Systems specialization.
Georgia Institute of Technology
Master of Science in Computer Science
2024 - 2026
Computational Biologist
Tempus AI
2021 - Present
Research Software Engineer
Indiana University - Newman Memory Lab
2019 - 2021
Indiana University, Bloomington
Bachelor of Science in Cognitive Science
2017 - 2021
Get in touch
Recruiter, hiring manager, or just curious — drop a short note and I'll reply within a day or two. For something more structured, the Opportunities page has roles, FAQ, and a calendar link.
© 2026 Maxwell Vaglica. All rights reserved.