I build intelligent systems, scalable backend platforms and data-driven products.
Passionate about Applied AI, Distributed Systems, Data Engineering, RAG architectures and recommendation engines.

• 🎓 Software Engineering student at FIUBA (GPA: 8.9/10)
• 🔬 Researching Multimodal RAG, retrieval systems and AI agents with LangGraph / smolagents
• 📊 Learning large-scale data processing with Apache Spark and modern data pipelines
• 🍎 Teaching Assistant for Algorithms & Programming courses at FIUBA
• 🎯 Open to internships / junior roles in AI Engineering, Data Engineering, ML Engineering or Backend

Languages:

Frontend & Mobile:

Backend & Infrastructure:

Databases:

Data Engineering & Analytics:

Machine Learning & AI:

Worked on a university research project building an assistant for Histopathology where both text and image retrieval are critical.

• Tech: Qdrant, Neo4j, ColPali, LangChain, LangGraph, LangSmith, RAGAS
• Evaluated retrieval quality, hallucination risk, relevance and production tradeoffs.
• Hands-on exposure to modern multimodal AI systems and retrieval pipelines.

Full-stack music platform built with a microservices architecture separating transactional, metadata and recommendation workloads.

• Tech: FastAPI, Go, Spring Boot, PostgreSQL, MongoDB, React, React Native
• Worked on APIs, service communication, scalable backend design and deployment.
• Strong practical experience in polyglot systems and product-oriented engineering.

Travel discovery platform focused on personalization, social connections and collaborative planning.

• Tech: Spring Boot, React + TypeScript, Neo4j, MongoDB
• Used graph modeling for recommendations and MongoDB for flexible content.
• Participated in product discovery and scalable backend decisions.

Concurrent distributed system designed to continue operating under failures.

• Tech: Rust
• Implemented timeout handling, crash recovery and coordinated workloads.
• Analyzed consistency, availability and resilience tradeoffs.

• Large-scale data processing with Spark / PySpark
• ML systems in production
• Recommendation engines
• Retrieval systems & agentic workflows
• Distributed backend architectures