Skip to content
View lpcoutinho's full-sized avatar

Block or report lpcoutinho

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
lpcoutinho/README.md

Hi, I'm Luiz Paulo Coutinho, a Backend Architect & Agentic Systems Specialist. 🖐

Github Linkedin Gmail

I am a Software Engineer specializing in Cloud-Native Backends, Microservices, and Agentic Computing. I architect distributed systems that bridge the gap between Large Language Models and real-world execution. With a strong foundation in Mathematics 🎓, I build scalable infrastructures—from event-driven microservices to reactive AI interfaces—where agents operate with precision and resilience. 🤖☁️

coding

🛠 Technical Specialization:

  • 🏗️   Microservices & Distributed Systems: Designing decoupled architectures using Django, Go, and FastAPI, focused on high availability and fault tolerance.
  • 🤖   Agentic Computing: Architecting autonomous agents using PydanticAI and LangGraph, integrated into microservices for complex task execution.
  • ☁️   AWS Cloud Architecture: Expert in AWS (ECS, RDS, S3, Lambda), implementing Infrastructure as Code (IaC) with Terraform and Kubernetes.
  • ⚙️   System Orchestration: Specialist in event-driven patterns, memory layers (Redis/Postgres), and state management for multi-agent workflows.
  • 🛡️   Reliability & Economy: Implementing Circuit Breakers, Semantic Caching (reducing costs by >40%), and PII filtering for safe autonomous operations.

🚀 Key Projects:

  • Omni-Bot Engine: A production-grade, multi-channel boilerplate for agentic systems, featuring intent routing and self-healing microservices.
  • Ops-Pilot: (Open Source) A Go-native agent that autonomously audits and manages Linux environments via natural language.
  • RAG-Umpire: (Open Source) An evaluation framework to test and validate the truthfulness of retrieval-augmented systems.

💬 Deep Dive with me on:

  • 🏎️   Polyglot Microservices: Scalability strategies in Go vs. developer velocity in Django/FastAPI.
  • ☁️   AWS Cost Optimization: Efficiently scaling LLM workloads and database instances.
  • 📉   Token Economy: Optimizing the cost and performance of generative agents.
  • 🔄   Agentic Handover: Strategies for human-in-the-loop and autonomous task transition.
  • 🥁   Culture: Maracatu, Capoeira, and building systems that flow.

Languages and Tools:


Pinned Loading

  1. workana-scraping workana-scraping Public

    Analyzing and Sending Workana's jobs data

    Jupyter Notebook 3 3