Arjun Puri
Computational Neuroscientist (prev. Software Engineer)
I'm a master's student at the Bernstein Center for Computational Neuroscience in Berlin, interested in the algorithmic principles of intelligence and how they translate between artificial and biological systems. Previously, I spent eight years building distributed systems as a Staff Engineer at Plaid. I hold B.S. degrees in Computer Science and Mathematical Sciences from Carnegie Mellon University.
Featured Projects
Decision Making in Low-Rank RNNs
Training low-rank RNNs on decision-making and working-memory tasks, building on Dubreuil et al. (2022). The connectivity statistics alone are enough to rebuild the decision network, but the working-memory network found a shortcut: it learned to keep time instead of remembering.
Slow Dynamics in Clustered Spiking Networks
From-scratch reproduction of Litwin-Kumar & Doiron (2012). A 5,000-neuron spiking network where clustered excitatory connections produce metastable dynamics and the kind of slow variability you actually see in cortex.
Background
Education
-
Bernstein Center for Computational Neuroscience
M.Sc. Computational Neuroscience
2025 - Present
-
Carnegie Mellon University
B.S. Computer Science & B.S. Mathematical Sciences
2012 - 2016
Experience
-
Plaid
Staff Engineer & Tech Lead, Core Services
2018 - 2025
-
Quantifind
Software Engineer, Data Platform
2016 - 2018