I'm a software engineer with a B.S. in Computer Science from St. John's University. I'm most interested in backend systems, machine learning, and the kind of technical work that turns rough ideas into software people can actually use.
Most of my recent work sits at the intersection of full-stack products, backend architecture, and applied AI. I enjoy building APIs, shaping platform systems, and turning strong technical ideas into software that feels practical, thoughtful, and durable.
I am especially drawn to work that rewards good engineering judgment and attention to detail, whether the goal is product execution, platform design, or research-informed problem solving.
Core languages and frameworks I rely on when shipping product work.
Modeling and retrieval tooling I use when building applied ML systems.
Storage, messaging, and delivery tools behind reliable production systems.
Driving platform engineering in an Agile/Scrum environment, turning product ideas into a working career-growth platform for students and early-career professionals. Owning the platform across the stack, from product development and scalable system design to deployment and platform operations.
Explored machine-learning and signal-processing methods for improving interference mitigation in lunar and low-frequency astronomy settings. Helped define a theoretical SDR-based approach targeting roughly 20 dB interference suppression and translated the work into proposal materials and a New Technology Report for potential NASA applications.
Distributed sentiment analysis platform that simulates a live tweet stream, classifies messages with a fine-tuned BERT model, and broadcasts real-time system state to an operator dashboard.
Browser-first PDF retrieval workspace for grounded document question answering with local embeddings, persistent vector search, and conversation-level source selection.
Job market intelligence platform that turns posting data into typo-tolerant search, normalized skill extraction, and interactive skill-demand graphs.
Computer vision and machine learning application that uses TensorFlow to analyze chest X-ray images and return confidence-scored predictions through a web interface.
