Summary
Manuel Valentín is a resilient ASIC design engineer and PhD candidate at Northwestern University with 11 years of experience building low-power, radiation‑resilient, and AI‑embedded silicon for high‑energy physics, quantum readout, and edge systems. His research blends neuromorphic and biologically inspired learning with practical RTL-to-GDSII implementation, exemplified by NRCSTK, a novel on‑device training framework that sidesteps backpropagation through local learning rules and metabolic constraints. He has bridged academia and industry through funded collaborations with Fermilab, CERN, Columbia, and Cadence, and brings hands‑on expertise in Python/PyTorch simulation, spiking neural models, HLS, and cryogenic/harsh‑environment digital design. Previously he applied deep generative and Bayesian models to geoscience at Petrobras and delivered power and sensing solutions in industry, giving him a rare combination of theoretical rigor and production‑grade silicon delivery. An engineer who thinks like a neuroscientist, he targets ultra‑low‑power adaptability for edge AI rather than mere throughput.
11 years of coding experience
7 years of employment as a software developer
MSc. Physics Physics, MSc. Physics Physics at Federal University of Rio de Janeiro
Doctor of Philosophy - PhD Computer Engineering, Doctor of Philosophy - PhD Computer Engineering at Northwestern University
UPC Universitat Politècnica de Catalunya
Spanish, Catalan, English, Portuguese, German