I'm an AI researcher at Cartesia, working on pretraining and scaling language models, infrastructure for large-scale distributed training, and scaling laws for H-nets.
Read more in our blog post, From Tokens to Bytes I: Scaling Hierarchical Networks.

I completed my PhD at Imperial College London through the Oxford-Imperial CDT in Mathematics of Random Systems, under the guidance of Dr. Cristopher Salvi. I completed my master's studies at Università di Pisa in 2022, with my thesis conducted at ETH Zürich under the supervision of Professor Josef Teichmann.

Here is a link to my PhD thesis, Graph expansions of neural networks: theory and applications for time-series analysis, if you'd like to read it and be transported into a world of graphs, trees, and their many combinations.

From February to May 2025, I interned at Cartesia.ai as a PhD Researcher, where I worked on distillation and multimodality.
From July to September 2025, I interned at Quadrature Capital, where I did lots of quanty things I'm not allowed to share.