AI and full-stack developer with a background spanning both technology and culinary leadership. Combines hands-on experience in Python, machine learning, and web development with years of working in fast-paced, high-accountability environments. Known for adaptability, disciplined execution, and a strong problem-solving mindset.
This website is serving as a place to learn, bringing personal and class projects to life and is a continuous work in progress.
Foundations
Technical Foundations
- Programming & Backend Development
-
- Python:NumPy, Pandas, scikit-learn, SciPy, spaCy, NLTK
- Web Frameworks:Flask, Django, FastAPI
- JavaScript:Node.js, Express.js
- REST API Design & Integration
- Artificial Intelligence & Machine Learning
-
- Model Development Concepts
- Data Preprocessing and Feature Engineering
- Data Visualization: Matplotlib, Seaborn, Plotly
- AI Systems & Retrieval Engineering
-
- Retrieval-Augmented Generation (RAG) Architecture
- Embedding Pipelines & Vector Storage
- Rule Based and LLM Systems
- Model Performance Optimization (CPU-bound environments)
- LLM Deployment via API (Express / FastAPI)
- Infrastructure & Deployment
-
- Linux VPS Hosting & Server Configuration
- NGINX Hosting + Reverse Proxy Setup
- PM2 Process Management
- Resource Constrained AI Optimization
It's Me!
Applied Systems & Experiments
onebadev.com - Chat Bot: BadBot
Originally developed as a rule-based Python chatbot for a Natural Language
Processing course, this assistant began as a structured Q&A system built
to recognize predefined prompts and return custom responses. While the early
version relied on pattern matching and scripted logic, the broader goal became
a bit more ambitious: evolve the chatbot into a system capable of intelligently
answering questions about my background, projects, and technical experience.
To support that idea, the project was rewritten in JavaScript to align with
my website's backend architecture. This transition established the foundation
for integrating large language models and retrieval-based techniques, with
the long-term objective of building a Retrieval-Augmented Generation (RAG)
system. The intent is for the chatbot to move beyond fixed responses and instead
dynamically retrieve relevant information about my work, education, and portfolio,
enabling a more natural, accurate, and context-aware interactions.
At its core, the project represents a shift from static question-answer logic
toward an intelligent, searchable knowledge assistant built around my personal
technical ecosystem.
- Backend:Node.js + Express.js (`POST /api/chat`), CORS
- LLM:Ollama (`ChatOllama`, Gemma model)
- Ingestion:DirectoryLoader (PDFLoader + TextLoader for `.md`)
- Chunking / Retrieval:RecursiveCharacterTextSplitter + Top-k retrieval
- Embeddings:OllamaEmbeddings (`embeddinggemma`)
- Vector Store:FAISS (`FaissStore`), with on-disk persistence (`faiss_index`)
Journal | Notes:
- Jan 14, 2026: The site itself has been up and running (and will continue to be), but after deploying BadBot to my VPS I have encountered a performance bottleneck. While responses were fast on my personal PC, the minimal, CPU only server (no GPU) has been struggling under the load. The model, Gemma3:1b, is too heavy for the available hardware, pushing the CPU to max out causing response times to rise. To hopefully solve this, I am currently downsizing the LLM to a leaner Gemma3:270M and reimplementing a lightweight, rule-based system to handle common questions quicker. In this hybrid setup, the AI model is only invoked for more complex queries, helping balance model capability with hardware constraints, keeping the site fast and responsive. Barring any issues with the updated model, (or anything else) upcoming improvements include lightweight in-session memory to further improve flow while maintaining hardware efficiency.
AI Agent Deep Learning Capstone
A collaborative deep learning capstone project focused on building an AI-powered process automation agent. We began with custom NLP tools and Python-based logic to interpret language input and automate workflows like e-mail responses, task creation, and calendar scheduling. The project later transitioned to the n8n automation platform, enabling faster development and integration of modular workflows without rebuilding core logic from scratch.
GitHub LinkAI Resources and Final Capstone
A proof of concept group project to validate that a lightweight, edge-deployable AI system running on Raspberry Pi can detect fire in real time and transmit location-tagged alerts via telemetry, demonstrating the feasibility of using the system in aerial or remote wildfire surveillance.
GitHub LinkBaseball Analysis System
This Python project started as a way to study and practice for my data analysis class at Houston City College and focuses on the analysis of pitcher and batter trends using historical MLB datasets. It leverages pandas and numpy for data manipulation, while matplotlib and seaborn generate visual insights into pitch selection frequency, dominant pitch types, and annual patterns. The system currently supports CLI interaction and player-specific breakdowns.
GitHub Link