Software engineer focused on automation, reliability, and thoughtful system design
Software engineer and quality leader focused on building reliable, well-tested systems that people can trust.
My work sits at the intersection of automation, embedded systems, and backend services, where correctness, observability, and long-term maintainability matter more than quick fixes. Outside of work, I stay active with chess, Brazilian jiu jitsu, and strength training. This site is a home for my projects, writing, and experiments—technical and otherwise.
Learn more about me →Some of my recent work and creations
A machine learning pipeline for prioritizing anomalous embedded-system test logs using Sentence Transformer embeddings and cosine similarity. Built for a CS 589 project, it compares several BERT-based encoders, normalizes timestamp-heavy data, and fine-tunes all-MiniLM-L6-v2 to separate abnormal and normal test runs without exposing proprietary log content.
A neural network-based stock price prediction system using Long Short-Term Memory (LSTM) networks. Built as a final project for CS 682 Neural Networks course at UMass Amherst. Implements a multi-layer LSTM architecture with dropout regularization, layer normalization, and early stopping for predicting daily stock closing prices.
A full-featured web application for generating detailed astrological birth charts with AI-powered interpretations, interactive chat, and synastry analysis. Built with Flask, PostgreSQL, and integrated with OpenAI/Anthropic for personalized chart readings.
Building and orchestrating teams of AI coding agents using Claude Code, OpenClaw, Codex, and Paperclip. Using agents to autonomously build features, write content, fix bugs, and run overnight — across multiple live projects simultaneously. Learning what works, what does not, and how to get the most out of AI-assisted development in real production environments.
A website built for Kelly McCarthy — breast cancer survivor, educator, and certified life coach. Kelly brings 8 years of teaching experience and a Masters in Education to her coaching practice, currently working at Boston University supporting students through mental health re-integration. Her niche: cancer survivors and caregivers navigating life after diagnosis. Built with Next.js, TypeScript, and Tailwind CSS.
Thoughts, tutorials, and insights
What I learned building a local anomaly-detection pipeline for high-volume embedded-system logs: preprocess the noise, test the embedding space, and fine-tune for the domain you actually have.
Read More →How four one-off exam tutors became private-by-design, offline-capable interactive study pages with instant browser-based feedback.
Read More →The optimal value function from reinforcement learning is the perfect heuristic for A* — not a metaphor, the same mathematical object. That one identity explains what learned heuristics are actually approximating, and why admissibility is the thing they risk losing.
Read More →Have a project in mind or want to collaborate? I'd love to hear from you!
Get In Touch