BrenoAV

GitHub LinkedIn Lattes ORCID Google Scholar
Profile picture of Breno

About Me

I have over 4 years of experience in the field of Artificial Intelligence, combining academic research with industry projects in areas such as computer vision, natural language processing, and time series forecasting.

  • 2024–Present — Master’s Degree Student (UFCG)
    Research Focus: Retrieval-Augmented Generation (RAG) for QA systems applied to Brazilian Grid Network Procedures
  • 2022–2024 — Researcher at Ford Motor Company
    Worked on projects involving computer vision (object detection), time series forecasting using statistical and machine learning models, and natural language processing (semantic search).
  • 2021–2022 — Scientific Initiation Scholar (PIBIC/CNPq – UFCG)
    Conducted research on computer vision, specifically in object classification tasks.
  • 2016–2022 — B.Sc. in Electrical Engineering (UFCG)
    Final Paper: Deep Learning for Industrial Surface Defect Classification

Outside of my professional and academic work, I enjoy running, watching TV shows and movies, listening to podcasts, and exploring astronomy content for fun.

Publications

Portfolio

Demo of Agentic Job Application Assistant

Agentic Job Application Assistant

A smart assistant that obtains information from natural language user input using the power of LLM tooling.
Technologies used: Python, Litellm, AI Agent
View on GitHub

Events

Third Place in DatathONS 2025

Participated in Hackathon provided by the National Electric System Operator (ONS) 2025, focused on making the open data portal (dados.ons.org.br) more accessible using Natural Language. Our solution, HorizONS, integrated RAG and AI Agent concepts for dynamic querying and data aggregation.

Technologies used: n8n, Python, Docker, Postgres

Presentation at SIMPASE XIV

Presented the work “Sistema Baseado em RAG para Consulta Inteligente aos Procedimentos de Rede do ONS” at the XIV SIMPÓSIO INTERNACIONAL DE ENGENHARIA ELÉTRICA E DE SISTEMAS (SIMPASE XIV), Foz do Iguaçu, PR, August 2025.

First Place in Hackathon CREA-PB 2025

Participated in Hackathon CREA-PB 2025, focused on transforming Crea-PB services using Artificial Intelligence. We developed an AI tool to automate completion of ART documents, streamlining validation and generation.

Technologies used: LangChain, Streamlit
View Publication →

Books

Technical Books

Introduction to Linear Algebra

Literature Books

2001
24 Hours in Ancient Egypt
A Brief History of Time
Animal Farm
Ative Sua Mente
Caesar's Last Breath
Charlotte's Web
Fantastic Mr Fox
Flamingo Boy
Foundation and Empire
Pai Me Compra Um Amigo
Psychology of Money
Second Foundation
The Curious Incident of the Dog in the Night-Time
The Foundation
The Story of Doctor Dolittle
Yes to Life