AI Engineer

Mike Arsolon

Building scalable LLM applications

VIEW MY WORK LEARN AI ENGINEERING

ABOUT

I'm a passionate AI developer specializing in Large Language Model applications and conversational AI. With a focus on creating intelligent, user-centric solutions, I build chatbots and text generation tools that bridge the gap between human communication and artificial intelligence.

My expertise lies in developing scalable AI applications using cutting-edge technologies, deployed on robust cloud infrastructure to deliver seamless user experiences.

Python
Bedrock
Vertex AI
AWS
GCP
Machine Learning
Prompt Engineering
Claude
Gemini
Chatbot

FEATURED ARTICLE

A Comparative Analysis of Chunk and Whole Document Vectorization for Knowledge Base Retrieval

Exploring the trade-offs between chunking strategies and whole document vectorization in RAG systems for optimal retrieval performance. This deep dive examines how different vectorization approaches impact search accuracy and system efficiency.

RAG Vector Search LLM Knowledge Base
READ ON MEDIUM →
PROJECTS

Cryptid History Generator

An interactive AI-powered tool that generates immersive, pseudo-historical accounts of cryptid encounters. Enter any cryptid name and receive a detailed journal entry-style narrative.

Claude API JavaScript CSS3 HTML5
START GENERATING

AI Support Assistant — Advanced RAG

A production-grade RAG pipeline for a fictional telecom's customer support. Watch every stage run live — query transformation, hybrid retrieval (S3 Vectors + BM25), reciprocal-rank fusion, two re-rankers compared side by side, and a grounded, cited answer.

S3 Vectors Hybrid Search Re-ranking Bedrock RAG
EXPLORE ADVANCED RAG

Tambayan Shoes — Design Lab

An interactive shoe customizer with zone-based SVG coloring and real-time 3D preview. Pick colors for every panel — upper, sole, laces, logo — and see your design update instantly on a rendered shoe canvas.

SVG JavaScript CSS3 HTML5
CUSTOMIZE SHOES
LEARN AI ENGINEERING

Retrieval-Augmented Generation (RAG)

An interactive, step-by-step walkthrough of how RAG systems work — from document ingestion and chunking, to embedding and vector storage, to retrieval and generation. Learn the pipeline hands-on.

RAG Embeddings Vector Store FAISS Python
LEARN RAG

Vectorization & Embeddings

How do you measure the distance between two ideas? A hands-on explainer that turns words into numbers you can add, subtract, and compare — with live experiments on real word2vec vectors, including the famous king − man + woman = queen.

Embeddings word2vec Vector Space Cosine Similarity NLP
EXPLORE EMBEDDINGS

BM25 & Keyword Retrieval

Semantic search understands what you mean — but sometimes you need the exact word: a part number, an error code, a surname. A hands-on build of BM25, the 30-year-old algorithm still running the web, one fixable problem at a time, with a live experiment for every knob.

BM25 Keyword Search TF-IDF Lexical Retrieval Ranking
BUILD BM25

CONTACT

Let's build something amazing together. I'm always interested in discussing new opportunities and innovative AI projects.

Email: michaelangeloarsolon@gmail.com
LinkedIn: https://www.linkedin.com/in/mikearsolon/
Location: Antipolo, Philippines
×

Cryptid History Generator

×

Document Q&A System

Upload a PDF document to start asking questions about its content.