Hi, I’m Marco Camilo,
I design, build, and operate deep learning systems that process natural language. I also specialize in data analysis and machine learning. Here are some of the projects in my portfolio:
AI-Powered Patient Journey Analytics
This project builds an end-to-end GenAI pipeline that transforms 50 synthetic IBD patient interview transcripts into structured, analyzable records using LLM-powered extraction with Pydantic schemas, chain-of-thought prompting, and confidence scoring. The pipeline combines classical NLP (TF-IDF, LDA/NMF topic modeling, VADER sentiment) with structured LLM extraction (Gemini 2.5 Flash via instructor + litellm) to answer four research questions about biologic treatment adoption, barriers, treatment patterns, and referral pathways.
LLM-Driven Resume Optimizer with Google Gemini and LangChain
This app leverages Google’s Gemini API and LangChain to evaluate and optimize resumes based job descriptions. Combining role prompting, task decomposition, and chain-of-thought, I enginered an AI-powered pipeline that identifies gaps, generates recommendations, and applies them to enhance resume-job alignement. The project integrates a cutting-edge AI pipeline to address a real-world challenge and significantly improve job seekers’ chances of success in the competitive job market.
BERT, Encoders and Linear Models for Resume Text Classification
This project evaluates the performance of advanced NLP models and vectorization techniques for text classifcation using a resume dataset. Implementing Linear SVC, FNN, Encoder models, and BERT, the project achieved an accuracy of 91.67% with BERT. The project demonstrates how to build efficient preprocessing pipelines, optimize feature representation to enhance resource usage, and develop high-performing text classification models using Scikit-Learn and PyTorch.
