I build backend systems, AI products, and internet experiments from zero.
Currently engineering at Mercado Libre and building Khora — an AI-native product for organizational intelligence. Based in Buenos Aires.
AI-native product for People Analytics and organizational intelligence. Goes beyond dashboards — it predicts, signals, and acts.
Competitive platform where autonomous agents play poker via REST API. Built around game loop architecture, agent isolation, and real-time state management.
WhatsApp bot for shared group expense management, powered by AI. Consumer-facing, natural language interface, zero friction for non-technical users.
Portable, spec-driven development kit with multi-agent orchestration. Turns technical specs into implemented code using a structured pipeline of specialized agents.
Scalable APIs, microservices, distributed architecture. Working at Mercado Libre means designing for billions of requests. Reliability is not optional.
Agent workflows, applied LLMs, productized AI. The interesting problems aren't in demos — they're in making these systems reliable enough to deploy.
From zero to shipped. Technical judgment and product taste are not separate skills. Building Khora taught me they're the same thing.
Architecture decisions, stack selection, technical tradeoffs for early-stage products. Boring technology for critical paths. Innovation where it actually matters.
Backend Software Engineer at Mercado Libre
Scalable backend systems at Latin America's largest e-commerce and fintech platform.
On building MVPs, confronting market silence, and iterating without ego. The loop that actually works.
Data reporting is not strategy. Real analytical value is forward-looking — signal detection, not passive charts.
The real bottleneck isn't tooling — it's the mental model. A systems-thinking take on HR and organizational intelligence.
Software is craft. I care about systems that work in the real world — not just in demos. Technical depth is leverage, not identity theater.
Shipping beats planning theater. The fastest feedback loop wins. I prefer a live product with rough edges over a perfect spec with no users.
No silos. I want to understand the product vision and the technical constraints simultaneously. Engineers who only see code miss half the problem.
I'm not interested in AI as a demo category. I'm interested in it when it connects to real workflows and changes how work actually gets done.
Choosing the right abstraction and choosing the right feature are the same skill. Code quality without product judgment is just expensive craft work.
If you're building something ambitious in AI, backend infrastructure, or early-stage product — I'm always interested in a good conversation.