Hey, I'm Saurya
Designing complex systems,
from first principles
Computer Engineering student focused on backend systems, distributed architectures, and AI infrastructure.
Exploring how intelligent systems reason, scale, and fail.
Featured Projects
Neural Network from Scratch
Implemented a multilayer perceptron in Golang from first principles to classify handwritten digits from the MNIST dataset.
TruMAN
A trustless mesh network for emergency communication using distributed peer-to-peer routing without internet dependency.
exoseekr
Deep Learning based exoplanet detection and visualization. Built for the NASA Space Apps Challenge, 2025.
ByByfarfarthethegreatestgreatestdangerdangerofofArtificialArtificialIntelligenceIntelligenceisisthatthatpeoplepeopleconcludeconcludetootooearlyearlythatthattheytheyunderstandunderstandit.it.
I build systems, then I try to understand how they fail.
I’m a Computer Engineering student @ Thapar, focused on backend systems, distributed architectures, and AI infrastructure. I enjoy working close to the metal of complex systems, where performance, reliability, and design trade-offs actually matter.
My current interests sit at the intersection of AI systems and research: agentic architectures, interpretability, and how large models reason, generalize, and break. I’m especially curious about making AI systems more transparent, controllable, and grounded in real-world workflows.
I like problems that are messy, multi-layered, and slightly underdefined, the kind where you have to model the system before you can even begin solving it.
Currently Reading on Goodreads
