Skip to content
View gpazevedo's full-sized avatar
🎯
Improving Scalability and Dev Experience, Reducing Costs.
🎯
Improving Scalability and Dev Experience, Reducing Costs.
3 followers · 9 following

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Block or report gpazevedo

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
gpazevedo/README.md

Hi there 👋

  • 🔭 I'm currently Building AI/ML Infrastructure & Platforms
  • 🌱 I’ve worked to improve Developer Experience in Generative AI, Agentic Systems, and Event-Driven Systems
  • 💻 Playing with Strands, LangGraph, MCP, KubeFlow, MLFlow.
  • 👯 I’m looking to collaborate on AI Open Source Projects
  • 🤔 I’m looking for Disruptive AI/ML Use Cases
  • 🚀 I'm learning BedRock AgentCore
  • 💬 Ask me about AI, Software Architecture, Observability, DDD, Data Mesh, CDC & Event-Driven Architecture
  • 📫 How to reach me: https://www.linkedin.com/in/gpazevedo/
  • ⚡ Fun fact: I feel like "I'm Back to School !"

Procurement Negotiation Agentic System (PNAS) This system was designed and developed through a deep integration of business strategy and high-fidelity engineering.

To ensure the technical solution addressed real-world needs, I began by researching the business domain to propose a commercially sound architecture. The design phase involved defining the core agent topology, governance models, and security posture, using PRDs with EARS requirements to maintain formal traceability from business goals to technical specs.

For the implementation, I built the end-to-end stack using Strands agents on Python 3.14, automating the deployment to AgentCore via Terraform and GitHub Actions. The system utilizes AppConfig for dynamic runtime configuration and includes dedicated strategies for observability and cost optimization.

Spring AI App deployed at AWS AgentCore Basic Generative AI app, built with Spring Boot 4, Spring AI 2 with full Observability, deployed at AWS Bedrock AgentCore

AI Teleprompter Browser-based AI Teleprompter for public speakers

Kafka Ingestor Contract-based production of Avro events from a JSON payload to a Kafka Topic. Service converts a JSON payload to an Avro payload based on a verified schema and publishes it to a Kafka topic, using the Outbox Pattern

Side Kafka

Sidecar that converts a JSON payload to Avro payload based on a verified schema and publishes it to a Kafka topic

Kafka DLQ on Apache Beam Kafka Dead Letter Queue on Apache Beam

Goals Service Goals Service

Event Modelling Hotel Event Modelling

CQRS Syncronous Bank API

ETL Hexagonal
Shop Accounting

Pinned Loading

  1. quiz quiz Public

    An AWS serverless application based on a GraphQL API. Tech Stack: JS, React, GraphQL, AWS AppSync, AWS Lambda, AWS DynamoDB.

    JavaScript 3

  2. clock clock Public

    A ticking console clock. Composing functions in JS.

    JavaScript

  3. prelegal prelegal Public

    A platform for drafting common legal agreements

    TypeScript

  4. spring-genai spring-genai Public

    Base Spring Boot 4, Spring AI 2 application with full Observability, deployed at AWS Bedrock AgentCore

    Java

  5. teleprompter teleprompter Public

    Browser-based AI Teleprompter for public speakers

    JavaScript

  6. stanford stanford Public

    Java