luiz — readme.md

home/luiz/readme.md

Hi — I’m Luiz Carlos.

role AI Backend Engineer
focus production AI · Python · data systems
now Auria AI · São Paulo, Brazil

I build and maintain production AI agents, FastAPI services, and the data platforms behind them for high-volume B2B security incident response.

20+production AI agents

3,000+daily security incidents

36production DB tables

Scroll to explore

01 · About

Engineering at the edge of data and AI.

I’m most useful where models, backend systems, and production reliability meet.

At Auria AI, I build and maintain Python AI agents across a production incident-response pipeline, spanning summarization, insight extraction, and automated decision-making.

I bootstrapped and maintain a PostgreSQL/SQLAlchemy data layer across 36 production tables and ship backend features across multiple FastAPI services, alongside monitoring, BI, and on-call alerting tools.

Previously, I helped migrate a large Ruby on Rails system to Kotlin at IME-USP. I hold a B.Sc. in Computer Science from the University of São Paulo.

Education

B.Sc. in Computer Science
University of São Paulo (IME-USP)
2020–2024

Languages

02 · Experience

Building, migrating, and leading.

Production engineering experience with a foundation in research, open collaboration, and technical leadership.

Aug 2025 — Present Engineering

Backend Software Engineer

Auria AI · São Paulo, Brazil

Build and maintain Python AI agents across the production incident-response pipeline, supporting 3,000+ daily B2B security incidents across 20+ agents.
Bootstrapped and maintain the PostgreSQL/SQLAlchemy data layer across 36 production tables, shipping features across multiple FastAPI services.
Built Auria’s Metabase BI from scratch, including operational dashboards, KPI analyses, and threshold-based alerts used daily by incident-response leadership.
Shipped a Twilio on-call bot with AI-generated incident summaries, reducing overnight outage detection from 8+ hours to near-immediate.

PythonFastAPIPydantic-AIPostgreSQLSQLAlchemyMetabaseTwilio

Jan 2021 — Aug 2023 Research

Software Developer · Research Scholarship

Hub USP Inovação · IME-USP

Migrated a large legacy Ruby on Rails system to a Kotlin backend, redesigning domain models, REST APIs, automated tests, and Docker deployment infrastructure.
Maintained AUSPIN’s innovation platform, serving 1,000+ patents, 3,000+ companies, 3,000+ professors, and 100+ innovation initiatives.

KotlinRuby on RailsREST APIsDockerAutomated testing

Jan 2021 — Mar 2024 Leadership

President & Member

USPCodeLab · IME-USP

Served as President from January 2022 to August 2023, leading 20+ members; organized two university hackathons, secured sponsorships, mentored participants, and managed event budgets.

LeadershipMentorshipEvent operationsWeb development

03 · Skills

A production-minded toolkit.

Backend-first, with the AI, data, and frontend range needed to take a product from an idea to production.

Backend

Core engineering

PythonFastAPIasyncioPydanticSQLAlchemyREST APIsMicroservicesPytest

AI & LLMs

Applied intelligence

AI AgentsRAGEmbeddingsPrompt EngineeringStructured OutputsLangChainPydantic-AIGeminiOpenAI APIClaude

Data & Tools

Production infrastructure

PostgreSQLSQLiteRedisDockerGitMetabaseTwilio APIVector SearchCI/CD

Frontend

Product interfaces

TypeScriptJavaScriptVue.jsReactHTMLCSS

04 · Projects

Ideas made useful.

Selected work across meeting intelligence and retrieval-augmented generation.

01 · Open source · 2026—Present

Memoir — AI meeting knowledge workspace.

Turns meeting transcripts into summaries, decisions, action items, participants, and structured transcript segments. Memoir automatically detects Zoom and Google Meet formats, with a Gemini fallback for messy or unsupported transcripts. Pytest coverage protects parsing and core flows.

FastAPIPydantic-AISQLAlchemySQLiteGeminiJavaScriptHTMLCSSPytest

View on GitHub

Memoir meeting workspace showing meeting summaries, decisions, action items, and transcript previews

02 · Capstone · AI / RAG · 2024

Divination — RAG assistant for Dungeon Masters.

A RAG assistant grounded in the official 2024 D&D Free Rules using LangChain, vector search, and GPT-4o. Built with a FastAPI backend and Vue 3 frontend as my B.Sc. capstone project at IME-USP.

PythonFastAPIVue 3LangChainGPT-4oVector Search

View project

05 · Contact

Let’s build something solid.

Open to backend and AI engineering roles, or collaborations on genuinely interesting products—based in São Paulo and available remotely.

Send an email View résumé

Emailluizcarloszdk@gmail.com

LinkedInin/luizcarlosdk

GitHub@luizcarlosdk