Skip to content
View MateusMPires's full-sized avatar

Block or report MateusMPires

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
MateusMPires/README.md

Hi, I'm Mateus Martins 👋

AI Software Engineer · LLMs & Full-Stack · iOS
I build AI-powered products end-to-end — from RAG pipelines and LLM integrations to apps people actually use.

LinkedIn Email App Store


🚀 About me

  • 🎓 B.Sc. in Computer Science (Universidade Católica de Brasília) & Apple Developer Academy graduate
  • 🤖 Specializing in applied AI & LLMs: built an end-to-end RAG system — chunking, OpenAI embeddings, vector search with pgvector, and evals to measure retrieval quality
  • 📱 7 native apps published on the App Store, owning the full product lifecycle: ideation → architecture → ASO → deployment
  • 🧩 Full-stack experience shipping B2B platforms with React, TypeScript, and Supabase (PostgreSQL + RLS)
  • 🗣️ Advanced English (Cambridge C1) · Portuguese (native) · Based in Brasília, Brazil 🇧🇷

🧠 What sets me apart

I don't just call LLM APIs — I engineer AI systems. My RAG project applies spec-driven development, a coding harness (CLAUDE.md), and automated evals to compare chunking strategies and systematically measure retrieval quality. Data comes from the system; language comes from the LLM.

I ship real products, not demos. From Ecos – Smart Journal (100+ downloads, 15 five-star reviews, first-submission App Store approval) to LocAlert, a real-time disaster tracker localized in 6 languages and presented to Brazil's Civil Defense.

I lead as well as I build. Product Owner & Scrum Master across multiple squads at the Apple Developer Academy, shipping apps in cycles under 3 months and pitching in English and Portuguese to evaluation panels.

🔭 Featured work

Project What it is Stack
RAG over Personal Notes Full retrieval-augmented generation pipeline: ingestion, chunking, embeddings, semantic search + evals for retrieval quality Python · pgvector/Supabase · OpenAI
Ecos – Smart Journal Native journaling app with biometric privacy (FaceID), widgets, and cloud sync — 100+ downloads, 15 ⭐⭐⭐⭐⭐ reviews SwiftUI · SwiftData · Supabase
LocAlert – Disaster Tracker Real-time disaster tracking, localized in 6 languages, with ChatGPT API integration — presented to Civil Defense Swift · MapKit · CloudKit · OpenAI
Kairon internal platform Web + mobile management platform: CRM with automated lead notifications, financial control, task tracking, RLS-based access React · TypeScript · Supabase

🛠️ Tech I work with

AI & LLMs — RAG · Embeddings · Chunking · Vector Search (pgvector) · Evals · Tool Calling · Prompt Engineering · Spec-Driven Development · OpenAI API

Languages — Python · Swift · TypeScript · JavaScript · SQL

Mobile (Apple) — SwiftUI · UIKit · SwiftData · CloudKit · WidgetKit · Combine · async/await · React Native

Web & Backend — React · Node.js · Supabase (PostgreSQL, RLS) · Firebase · RESTful APIs

Practices — MVVM · SOLID · Clean Code · Unit Testing · Evals · CI/CD (Xcode Cloud, Jenkins) · Git/GitHub

📊 GitHub stats

GitHub stats Top languages


💬 Open to opportunities in AI Engineering, iOS, and Full-Stack — let's talk: mateusmp.df@gmail.com

Pinned Loading

  1. rag-docs-context-search rag-docs-context-search Public

    🔎 Semantic search / RAG over devotional notes with OpenAI embeddings and pgvector on Supabase. An AI Engineering learning project: "data comes from the system, language comes from the LLM."

    Python

  2. ReactNative-Supabase-Auth ReactNative-Supabase-Auth Public

    A Swift developer's first dive into React Native. Exploring Expo Router, Native Tabs (Liquid Glass), and Supabase Auth in a clean architecture lab.

    TypeScript

  3. Swift6-Concurrency-Lab Swift6-Concurrency-Lab Public

    Laboratório prático de Concorrência Moderna no Swift 6. Explorando pipelines de dados assíncronos com TaskGroups, isolamento seguro com genéricos (Actors) e arquitetura nativa focada em Cache-First.

    Swift 2

  4. Swift6-Localization Swift6-Localization Public

    Projeto de localização (i18n) para iOS. Demonstra o uso de String Catalogs, formatação nativa e resiliência de UI com SwiftUI.

    Swift

  5. trip-health-forms trip-health-forms Public

    Multi-tenant, offline-first platform to collect and manage missionary travelers' personal, health and consent data (Next.js · Expo · Supabase RLS · LGPD).

    TypeScript