Bridging Research and Production
“Data is just a collection of points until it’s connected.”
I am an AI/ML Engineer designing and building systems that take models from research into production, with experience across NLP, LLMs, RAG, and recommender/search systems. My background in linguistics shaped this focus — I’m currently completing my Master’s in Language Technologies & Digital Humanities at the University of Turin, where my thesis tackles contrastive synthetic augmentation for LGBTQ+ slur reclamation. I bring a global perspective from professional and academic work across Italy, Germany, and Iran.
A recurring thread in my work is spotting where standard methods break on edge cases — fixing tokenizer vocabulary gaps for crypto terminology, or introducing a new scoring metric (MPEC) to separate agent from patient roles in slur reclamation — and building the fix myself rather than working around it. I combine this with a strong MLOps foundation: building scalable, production-grade ML pipelines using Python, PySpark, and AWS.