The Foundation
Sapienza gave me a rigorous grounding in computer engineering fundamentals: from transistors to operating systems, from data structures to distributed systems. The curriculum was broad by design, and that breadth turned out to be invaluable.
What I Studied
The core areas spanned the full stack:
- Algorithms & Data Structures: complexity theory, graph algorithms, dynamic programming
- Computer Architecture: CPU pipelines, cache hierarchies, memory systems
- Operating Systems: process scheduling, virtual memory, file systems, concurrency
- Database Systems: relational algebra, SQL optimization, transaction isolation
- Signal Processing & Control: the mathematical foundations that later proved essential for computer vision
The Turn Toward AI
In my second year, I took introductory ML courses and was immediately drawn to the intersection of systems and intelligence. I started exploring deep learning independently, which led to opportunities in the AI/ML lab as a research assistant.
Thesis: SplatSLAM
My thesis research pioneered real-time 3D reconstruction using Gaussian Splatting for SLAM pipelines. The project involved:
- Adapting Nerfstudio's offline rendering pipeline into a real-time incremental system
- Implementing photometric tracking for camera pose estimation
- Evaluating the system on indoor dynamic sequences
This work was developed within Sapienza's Honors Program (top 1% of students) and directly led to my interest in GPU kernel optimization.
Graduating
I graduated with 110/110 cum Laude (highest distinction). The experience at Sapienza was defined by two things: the rigor of the engineering curriculum and the freedom to explore AI research alongside it. Both shaped everything I've done since.