Espírito Santo, Brazil · open to remote opportunities

LUCAS GARCIA / AI · DATA · SOFTWARE

Lucas Garcia: data, AI and software.

32 audited repositories and 7 real case studies with verifiable code, decisions, metrics and limitations.

DATA INTELLIGENCE PRODUCT
LAT 19.532°S · LON 40.630°WLIVE SYSTEM INDEX
SYSTEMS MAP / 01

From data to product

Select an atlas region

A.01P.12

INTELLIGENCEModels, RAG, baselines and evaluation.

SELECTED SYSTEMS / 01—07

Projects connecting the whole stack

Each system record starts with the problem and ends in public links, stack, evidence and limitations verified in the repository.

SYS-02LIVE DEMO
Data quality · analytics productPublished on GitHub

AI Data Quality Checker

Analyze CSV files repeatably, reveal quality issues and generate practical cleaning recommendations.

EVIDENCEQuality score

Detects nulls, duplicates, cardinality issues, inconsistent types, empty and constant columns, problematic names and outliers.

SYS-03LIVE DEMO
Web system · institutional managementPublished on GitHub

Portal Paroquial Integrado

Organize parish administration, pastoral workflows, public communication and governance with secure module-based access.

EVIDENCECRUD + audit

Implemented vertical flow: create person, view person, edit person and audit changes.

SYS-04LIVE DEMO
ChatOps · runbook assistantPublished on GitHub

Pass-To-Pass

Answer operational incidents from local runbooks with diagnosis, checklist and traceable sources.

EVIDENCERunbook RAG

Delivers diagnosis, resolution steps, copyable checklist, sources, confidence, feedback and operational metrics.

SYS-05LIVE DEMO
ETL · remote jobs analyticsPublished on GitHub

VagasInLine

Collect, normalize and analyze international remote jobs from public sources and structured files.

EVIDENCEMedallion ETL

Includes Bronze/Silver/Gold, Data Quality, Schema Drift, Data Lineage, CSV/Parquet/Markdown/HTML exports and a safe scraping policy.

SYS-06LIVE DEMO
Machine Learning · PNAD ContinuaPublic-code capstone project

Previsor de Renda

Estimate monthly income from socioeconomic and occupational features with methodological rigor and interpretability.

EVIDENCER² 0,5913

Documented evaluation on 25,801 observations: CatBoost reached 0.5913 log-scale R² and the hybrid model reached 0.4906 R² on the original scale.

SYS-07LIVE DEMO
Cloud · infrastructure as codeImplemented academic project

SmartClass IaC

Turn a manual full-stack deployment into declarative, repeatable infrastructure on AWS.

EVIDENCETerraform + ECS

The repository contains 96 files, three Terraform modules and Docker images for frontend and backend, plus the full-stack application.

07 / 32 selected cases / audited repositoriesView full inventory
LAT 19.532°S · LON 40.630°WLIVE SYSTEM INDEX
SYSTEMS MAP / 01

From data to product

Select an atlas region

A.01P.12
FIELD NOTES / EXPERIENCE

Public projects, documentation and technical delivery.

The focus is making evaluation easier for recruiters: open code, READMEs, pipelines, tests and objective case studies.

Experience
  1. 01
    Sep 2025 - Aug 2026

    Scientific Initiation Fellow in Artificial Intelligence

    Ifes · Campus Colatina · PRPPG/PICTI

  2. 02
    Volunteer extension

    Software Quality and Testing at LEDS

    LEDS · Ifes

  3. 03
    2026

    Income Predictor (Undergraduate Capstone)

    Ifes · Campus Colatina

RESEARCH GARDEN / NOTES

Learning documented, not hidden.

N.0308 MIN
Product note · Published

Data quality as a product experience

Scores, recommendations and reports reduce the distance between technical diagnosis and action.

  • Data Quality
  • FastAPI
  • Vue
OPERATING PRINCIPLES

How I work

01

Evidence before opinion

Decisions get metrics, logs, tests and limits.

02

Architecture serves the problem

Complexity enters when it proves value.

03

End-to-end reliability

Data, APIs, interfaces and documentation share quality.

NEXT COORDINATE / CONTACT

Recruiting for data, AI, backend or full-stack product work?

Let’s talk