João Víctor López Matias
Brazilian AI engineer building agentic systems, retrieval infrastructure, and product-grade experiences that actually ship. I work across multinational AI workflows, founder-led product design, and the long arc of building globally from Brazil.

Currently shipping
Multinational AI systems by day, Astrea by night.
Product proof, narrative context, collections, and an AI layer that feels central instead of ornamental.
Quick route
Open Astrea in detailThe project where product instinct, AI architecture, and symbolic UX all meet.
Current role
AI Integration Engineer
Shipping agentic workflows, retrieval systems, and operational AI inside FI Group.
Founder build
Astrea
An AI-native product for astrology, ritual, and emotionally resonant interaction design.
Global chapter
Stanford Summer 2024
A formative bridge between Brazil, Silicon Valley, systems thinking, and founder ambition.
Execution arc
Computer vision + RAG
Production AI delivery across computer vision, retrieval, research, and product systems.
Astrea is João's clearest consumer AI product surface.
A ritual-first mobile experience where symbolic interaction, live context, and memory-aware guidance are treated like a real product system, not a novelty layer.
A structured walkthrough of the current Astrea build.
Astrea is João's most productized consumer AI build right now: a premium mobile experience around ritual, live sky context, emotionally intelligent guidance, and dream-aware reflection.
The walkthrough below is organized the way a founder would explain the product to a sharp early user, product designer, or YC reviewer: what the user sees, what the interaction is doing, and why the system feels differentiated.
It is designed like a real product surface, not a content feed with an API taped on top.
Ritual foundation
Intention-setting flows that make symbolic interaction feel tactile and deliberate.
Live sky layer
A cosmos surface that gives the product atmosphere, orientation, and daily relevance.
Witness conversations
Constellation-specific guidance that makes the AI feel native to the category.
Dream rituals
A second behavioral loop around sleep, recall, imagination, and memory-building.
Current preview focus
Venus intention flow
A symbolic ritual that turns desire into a tactile, premium interaction.
Astrea starts from emotional UX, not generic chat. This screen turns a Venus moment into a guided action: choose the intention, write the commitment, and let the interface make the ritual feel deliberate.
Walkthrough structure
Screens `1–10` are organized into product chapters so the demo reads like a launch-story surface, not a screenshot dump.
AI João
Grounded by story, proof, and memory.
The AI layer is designed to feel like a real founder interface, not a bolted-on chat widget. It understands João's collections, projects, milestones, and public proof so visitors can navigate the site through conversation.
Featured Projects
The products and systems behind the trajectory.

Education / Founder Formation
Stanford Experience
A summer 2024 Stanford chapter that expanded João's work across high-performance computing, AI, energy, and founder ambition.

Consumer AI
Astrea
An AI-native astrology and self-reflection product designed around ritual, memory, symbolic interfaces, and emotionally resonant guidance.

Applied AI
Computer Vision Demo
A public demo capturing João's production-minded computer vision work, from PPE detection to posture and sentiment use cases.

Recognition / Community Building
Huawei Ambassador
Early national recognition through Huawei ICT Academy, including standout ambassador status and the creation of Huawei Club Unifor.
Collections
A founder archive organized by chapter.
The site now works like a story universe: Stanford, YC, Paris, infrastructure, and product-building moments grouped into intentional collections instead of a flat gallery.

Summer 2024
Education & Global Exposure
Stanford Visiting Student — Summer 2024
A global academic and founder inflection chapter.
A summer inside Stanford's ecosystem that deepened João's technical range in AI systems and his conviction around global founder execution.
2024
Startup Ecosystem
YC Startup School — San Francisco 2024
Early pattern-recognition inside the YC ecosystem.
A compact archive of João's 2024 YC Startup School exposure while already leaning into AI product execution.

2025
Founder Journey
YC Paris Startup School 2025
Founder momentum carried into Europe.
A richer founder-story collection from Paris showing YC-adjacent energy, network density, and João's continued global startup orientation.
Project Gallery
Projects and proof
A working archive of products, proof, and technical systems behind João's builder trajectory.
Story
About
João Víctor López Matias is an AI engineer from Ceará, Brazil, building at the intersection of systems, product, and interface. He studies Computer Engineering at Unifor, has shipped production AI systems across multiple domains, and approaches software as something that should feel both intelligent and intentional.
In 2024, he became a visiting student at Stanford, where he studied high-performance computing, energy, creativity, and startup thinking inside the environment that shaped Silicon Valley. The experience deepened his conviction that technology should not be treated as isolated code, but as a vehicle for products that change how people think, work, and create.
Before and around that chapter, João built a reputation in Brazil for taking initiative early. He was selected as a Huawei ICT Academy ambassador, founded the Huawei Club Unifor, earned national recognition through the program, and used those opportunities to align education, community-building, and emerging technology around real outcomes.
Professionally, his work spans computer vision, retrieval systems, legal AI research, and agentic internal tooling. At Moldsoft, he shipped production computer-vision systems; in research, he worked on legal classification and hybrid retrieval; and at FI Group he focuses on internal AI workflows, RAG infrastructure, and deployment-minded systems for real business teams.
Today, that technical depth is converging with a stronger founder identity. Astrea represents that next phase: a consumer AI product that blends symbolic interface design, ritual, emotional UX, and agentic behavior into something more alive than a static app. The throughline across all of João's work is the same: build products that are elegant on the surface, rigorous underneath, and meaningful enough to matter in the real world.

Stanford, summer 2024.

High-performance computing and systems exposure during the Stanford experience.
Press and public proof
A horizontal rail of public signals around João's trajectory.
article
Unifor spotlight on João's Stanford exchange
Unifor documents João as a Computer Engineering student completing a summer exchange at Stanford in 2024, highlighting his AI focus, Huawei background, and immersion in Silicon Valley entrepreneurship.
article
Unifor coverage of Huawei ICT Academy recognition
Unifor reports that João was selected as one of six Huawei ICT Academy ambassadors in Brazil and later received standout ambassador recognition, tied to founding the Huawei Club Unifor and expanding technology education initiatives.
article
Unifor interview on João's international technology path
A later Unifor interview frames João's Stanford experience, Moldsoft AI work, Huawei recognition, and FUNCAP legal AI research as part of a broader international trajectory in technology.
social
LinkedIn profile
Public professional profile describing João as an AI engineer focused on scalable RAG, agentic AI, and computer vision, with Stanford and EuroTech listed among his signals.
Contact
Build something ambitious with me
Open to founder conversations, product opportunities, and ambitious AI work that deserves taste as much as technical depth.
Late-Night Build Log
