GPT-1 public release
Following GPT since its first public release.
Full Stack Engineer based in Rome, Italy
I build software across frontend, backend and AI systems.
A simple view of my growth from first role to today, with work on the left and AI on the right.
Following GPT since its first public release.
Java, Spring Boot and first steps in enterprise software.
Liferay, React and delivery on strategic public platforms.
Deeper focus on practical AI usage and experimentation.
Technical leadership on critical architectures and system design.
Currently at Almaviva, working across critical systems.
RAG, LangChain, Qdrant and production-ready AI workflows.
PyTorch, TensorFlow, LLMOps, Fine-Tuning, Multi-Agent Systems, LangChain, LlamaIndex, Qdrant, Pinecone, RAG Architectures, OpenAI API, DeepSeek, Claude, Prompt Engineering, Computer Vision, Hugging Face, Datapizza AI
Java, Spring Boot, Microservices, Event-Driven Architecture, Apache Kafka, RabbitMQ, gRPC, Python, FastAPI, Node.js, Serverless, PostgreSQL, MongoDB, Redis, OracleDB, REST, GraphQL, System Design, C / C++
React, Next.js, Astro, TypeScript, Tailwind CSS, Shadcn UI, Framer Motion, Zustand, Three.js, Microfrontends, Bootstrap, HTML5 / CSS3
Docker, Kubernetes, Terraform, IaC, AWS, GCP, Azure, Prometheus, Grafana, Git, GitHub Actions, CI/CD Pipelines, Maven, Gradle, Linux, Bash, System Security
Electron desktop app to orchestrate multiple CLI sessions, embedded terminals and shared workspaces.
Multimodal AI experiment that reads live traffic by rendering maps, taking screenshots and using vision analysis.
Festive RAG-based app to analyze Elf CVs with a FastAPI backend and a Next.js frontend.
Three-agent pipeline that creates personalized scientific bedtime stories for children.
Minimal ingest and RAG pipeline over GitHub documentation using OpenAI and Qdrant.
If you want to build a product, improve an existing platform or work on AI solutions, feel free to reach out.