AI Software Engineer
I build end-to-end AI software, from model optimization and inference pipelines to backend services, agentic systems, and desktop/web applications.
AI & Inference
LangGraph · RAG · Tool Calling · Knowledge Distillation · Quantization · ONNX Runtime · llama.cpp
Backend & Systems
FastAPI · Axum · Tokio · NestJS · WebSockets · Server-Sent Events
Data & Retrieval
PostgreSQL · pgvector · Qdrant · FastEmbed · Redis · SQLite
Frontend & Desktop
Vue 3 · Single-SPA · Vite · Storybook · TailwindCSS · Playwright
Engineering & Observability
GitHub Actions · Pytest · Jest · OpenTelemetry · Prometheus
I started learning computing long before it became my profession, moving from hardware, Linux, web systems, and programming into software engineering and artificial intelligence.
In parallel, I studied Law at the University of Buenos Aires. That background shaped the way I approach engineering: paying close attention to rules, edge cases, traceability, conflicting constraints, and the consequences of system failure.
Over time, those two paths converged. Today I work primarily on AI and software systems, with particular attention to reliability, safety, and maintainability.
My work spans AI engineering and general software engineering.
I have worked on RAG pipelines, agentic workflows, model optimization and inference, backend services, automation systems, computer vision, conversational AI, and desktop/web applications.
Depending on the problem, that may involve designing an agent state graph, optimizing a model for CPU inference, building services in Rust or Python, implementing retrieval systems, or developing the application around the AI itself.
I am interested in building useful systems for real-world problems, not AI as an isolated component.
I pay particular attention to failure modes, input validation, latency, observability, resource usage, maintainability, and the behavior of probabilistic components under real-world conditions.
I design systems so that important behavior can be inspected, tested, measured, and improved. When reliability matters, I try to keep critical decisions explicit and place clear boundaries around components whose behavior is inherently probabilistic.
Performance matters to me, but so does keeping complexity under control and understanding why a system behaves the way it does.
I want to continue growing in AI systems engineering, particularly around model inference, optimization, agent architectures, and high-performance software.
I am especially interested in the boundary between AI and systems engineering: efficient runtimes, resource constraints, native software, distributed services, and architectures that make increasingly capable models practical and reliable.
My goal is to build useful technology in industry while continuing to deepen the engineering behind it.
Bachelor of Laws (LL.B.)
University of Buenos Aires
Based in Tokyo, Japan