AI, Systems, and Cloud Solutions
Transform your ideas into custom Web Apps, APIs, and AI Agents. From coding to cloud infrastructure management.
About Me
Hello! My name is Rafael. I am an Information Systems professional with a focus on three areas: Artificial Intelligence, Systems Development, and Cloud Infrastructure.
I develop modern applications and build the necessary cloud infrastructure to keep them online with high availability, security, and optimized costs. My focus is on connecting development, automation, and cloud architecture to transform needs into efficient systems.
My expertise is backed by official Oracle Cloud (OCI) certifications in infrastructure, data, and artificial intelligence, as well as a professional IT Support certification from Google, ensuring compliance with best market practices.
Specialized in the Python and TypeScript ecosystems, I integrate solutions such as AI agents, local/cloud inference engines, and edge computing to deliver robust APIs and intelligent automations.
Solutions
My work is about simplifying technology for you, combining software development with the necessary infrastructure. I divide my services into three main areas:
Artificial Intelligence
Development of autonomous or supervised agents, multi-agent architectures, automations, and deployment of inference engines.
Systems Engineering
Building web applications, native desktop systems for Windows and Linux, APIs, and end-to-end process automation.
Cloud & SysOps
Computational provisioning, virtual network configuration, access security, server, container, and database management.
Projects
AI-BloodMatch
An artificial intelligence agent focused on interpersonal affinity analysis. The application uses the popular Japanese belief Ketsueki-gata to interpret compatibility between personalities based on blood types. By interacting with the user, Blood Match processes the provided information and offers a personalized analysis of harmony and connection points between different profiles.
AI-ChatLLM
A lightweight and straightforward local Desktop Playground designed to connect multiple LLM providers and models via LiteLLM in a ChatGPT-inspired interface, with local storage via SQLite and fast execution using uv.
AI-RouterLLM
An intelligent proxy server that runs silently in the background, centralizing the management of your API keys and allowing you to create custom endpoints to securely and efficiently integrate any AI tool.
Multi-Engine AI Gateway
A centralized Python AI inference gateway that automates the routing and execution of multiple engines (vLLM, Llama.cpp, ONNX, OpenVINO, and TorchServe), natively identifying the model format (.gguf, .onnx, .safetensors, .pt, .xml).
Contact
Send a message and let's talk about how I can help transform your ideas into reality. I'm here to answer questions, discuss projects, and find the best solution for you.