Senior Backend Engineer with 8+ years of experience building scalable backend systems, APIs, and enterprise platforms across healthcare, government, and business domains.

I specialize in designing reliable systems with strong data integrity, auditability, and real-world operational impact — especially in environments where accuracy, traceability, and operational control are critical.

Currently expanding my work into AI-assisted backend systems using LLMs, RAG, vector databases, asynchronous pipelines, and worker-based processing.

• Design and build scalable backend systems
• Develop RESTful APIs and business workflows
• Create systems for healthcare operations and surgical material traceability (OPME)
• Implement clean architecture and maintainable codebases
• Improve reliability through data integrity, auditability, and process automation
• Build AI-assisted applications using LLMs, RAG, embeddings, and background workers

Backend

• PHP (Laravel), Node.js, Java (Spring Boot) Improving

Database

• MySQL, PostgreSQL, MongoDB, Cassandra Improving
• pgvector for vector search and AI-powered retrieval

AI & LLM Engineering

• LLM integration, RAG pipelines, embeddings (OpenaI, Gemini, Ollama)
• Vector search, semantic retrieval, reranking (Cohere)
• AI-generated content, explanations, and quiz generation

Architecture & Engineering

• Clean Architecture, SOLID principles
• REST APIs, Microservices, Distributed Systems
• Event-driven and worker-based processing

DevOps & Infrastructure

• Docker, CI/CD, GitHub Actions
• Redis, RabbitMQ
• BullMQ, queues, workers, and background jobs

HealthTech platform for surgical material traceability, auditability, and workflow control.

• Tracks OPME materials at unit level, including lot, serial number, and expiration date
• Provides audit trails across surgical and operational workflows
• Helps reduce operational risks, billing inconsistencies, and glosas
• Built with Laravel, MySQL, and Docker

👉 https://github.com/Gabrielz11/OrtoTraceability

AI-powered learning platform with adaptive quizzes and modular architecture.

• Generates dynamic questions and explanations with LLMs
• Uses RAG to retrieve relevant educational content from uploaded materials
• Supports embeddings, vector search, and pgvector-based retrieval
• Uses asynchronous processing with queues, BullMQ, and workers
• Provides role-based access for students and teachers
• Uses a backend-driven architecture with Next.js and Prisma
• Built with PostgreSQL database

👉 https://github.com/Gabrielz11/networking-quiz-platform

🤖 AI-ML Learning Lab

Interactive educational platform for learning Machine Learning concepts through practical execution and AI-assisted explanations.

Demonstrates supervised learning concepts with classification and regression modules Uses real ML datasets to explain model behavior, metrics, and predictions Includes an inference simulator with dynamic AI-generated explanations Combines Python/FastAPI backend with a modern frontend interface Shows practical foundations in Machine Learning, model evaluation, and AI-assisted education

👉 https://github.com/Gabrielz11/AI-ML-Learning-Lab

Currently focused on:

• Cloud Architecture (AWS)
• Distributed Systems
• Event-driven architectures
• HealthTech systems and compliance
• AI-assisted backend applications
• LLMs, RAG, vector databases, and AI pipelines
• Background processing with queues, workers, and asynchronous jobs

• HealthTech and high-impact systems
• Scalable platforms and cloud-native applications
• AI-assisted software products with real-world operational value

• LinkedIn: gabrielvazaires
• Email: gabrielvazaires.pro@gmail.com

⭐ Always building, always improving.