Hey there 👋

I'm Gabriele

ML/AI Engineer and EU Vulcanus Fellow in Japan (one of 23 selected across Europe from 500+ applicants). I work at the intersection of research and production: real-time speech-to-animation systems, agentic LLM pipelines, and open-source privacy-focused NLP tooling. Previously shipped RAG infrastructure and agentic workflows to production as a Data Scientist. I care about systems that hold up outside the lab. Feel free to explore my projects and blog to see what I'm up to! 🚀

My last projects

NerGuard
Master Thesis

A privacy-focused tool designed to detect PII quickly, enabling secure RAG and privacy-first AI applications.

SynapseLink
Publication

real-time audio-driven facial animation system generating 52 blendshapes at 25 fps (204× faster than real-time, single GPU). Designed a custom training objective for expressiveness (+91.8% over baseline), achieving a 7–43× lighter model than FaceFormer/CodeTalker.

NerGuard Master Thesis

SynapseLink Publication

NerGuard
Master Thesis

SynapseLink
Publication