Nathanael Castro — Software Engineer & AI Builder

ai builder

Ships AI products people actually use: chatbots, RAG pipelines, and agents.

<engineer>

Full-stack developer who writes clean, tested, production-ready code.

Nathanael Castro · Software Engineer · South Florida

Move your mouse ←→

About

Both halves are true. I'm a full-stack engineer who treats AI as a material, not a magic trick.

Recent CS grad from Florida Atlantic University with a minor in AI and Cybersecurity, and the only intern engineer on a live production system at OneHope. I've shipped chatbots, mobile apps, database redesigns, and browser agents. I like hard problems with real users on the other end.

it follows your cursor · webgl

Selected work · hover a row

TT Truth Talks AI Bible app for kids · React Native Kids talk with AI biblical characters in real time. Full stack with COPPA-grade moderation and parental controls. NF NutriFit AI fitness platform · hackathon AI meal and workout planning with dashboards and weekly planners, shipped before the hackathon clock ran out. FR Frank AI budgeting assistant · TypeScript A fanatical budgeting assistant with blunt, actionable advice. Frank is not gentle. That's the point. LC llm-in-chrome open-source browser agent An open-source browser agent that works with any LLM. Reads pages, takes actions, provider-agnostic. EC El Camino AI trip planner Plans whole trips around your preferences: routes, stops, and pacing, not a generic itinerary dump.

Proof of work

I build AI assistants for a living, so here's a small one. Fully scripted, zero API calls, because a portfolio shouldn't burn tokens. The production versions are above.

castro.bot scripted · 0 tokens harmed

Ask about Nathanael

Experience

Jun → Aug 2025
Pompano Beach, FL

AI Software Engineering Intern

OneHope

Sole intern engineer, no safety net. Built and deployed an AI chatbot on the OpenAI API, Node.js, and MongoDB that lets employees retrieve information, answer event questions, and auto-generate meeting summaries.

Architected a full MongoDB redesign for a production system monitored with AWS CloudWatch, improving query performance and scalability.

Ran A/B tests and focus groups with 35 participants to drive feature decisions, then built the backend survey flows and shipped the frontend conversation starter UI myself.

Toolkit

LanguagesPython/JavaScript/TypeScript/C++/Java

AI & MLOpenAI API/LLM integration/RAG & embeddings/prompt engineering/content moderation

FrameworksReact/React Native/Node.js/Express/EJS

DataMongoDB/Supabase (PostgreSQL)/schema design/REST API design

Cloud & opsAWS CloudWatch/Git & GitHub/CI/CD/Vercel

PracticesAgile/A/B testing/COPPA compliance/API rate limiting

Education & certifications

May 2026

Florida Atlantic University

B.S. in Computer Science with a minor in Artificial Intelligence & Cybersecurity. Coursework in data structures & algorithms, database systems, software engineering, full-stack development, iOS development, and AI.

Certifications

Google AI Essentials · HackerRank Python (2026) · Microsoft Foundation C# (in progress)