AI Engineer · Agent Systems Architect · São Paulo, Brazil

I build AI systems that remember better, retrieve smarter, and stay useful over time.

From agent memory architectures to low-resource language models, I'm interested in systems that carry context, adapt, and do real work outside the demo.

About

Jorge Guberte

I'm a software engineer focused on AI systems, agent architectures, and interfaces for working with context over time. I'm especially interested in memory models, retrieval, orchestration, and the weird edge where software starts behaving more like a cognitive system than a static tool.

Read more about my work →

Now

  • Designing and refining the Y2K Sensory Design System for neurodivergent accessibility.
  • Exploring long-term memory, context engineering, and MCP workflows.
  • Running and testing LLM inference systems on Modal.
  • Designing AI products and agent workflows at Hub Esfera.

Selected Work

Projects with a strong point of view.

01

Y2K Sensory Design System

A brutalist-inspired design framework unifying maximalist Y2K aesthetics with strict neurodivergent accessibility (AttentionGuard).

Built with a dual-layer CSS architecture to isolate decorative animations from functional UI, offering tailored cognitive presets for TDAH and Autism.

HTML/CSSThree.jsAccessibilityDesign

02

Multiverse

A state management library with Git-style branching semantics.

Useful for applications that need forkable state, experimentation, and timeline-safe UX patterns.

TypeScriptStateReact

03

Ayvu-Talian

A decoder-only transformer trained for Talian, a minority language spoken in southern Brazil.

An exploration of low-resource NLP, language preservation, and model-building from scratch.

NLPPyTorchLow-resource LMs

Labs

A playground for useful weirdness.

Static, fast, and intentionally scrappy. Interfaces, experiments, tiny tools, and prototypes before they deserve a product page.

Visit Labs →

Writing

Notes from the builder side of AI.

Notes on memory, context, infrastructure, and the realities of building AI systems outside toy demos.

Browse all writing →