Summary
Shahan Nercessian is a senior applied researcher and audio AI specialist with nearly a decade of professional experience and a PhD in electrical engineering from Tufts. He has driven production-ready ML and DSP systems at leading audio companies (iZotope, Native Instruments, and now Splice), contributing features to award-winning products and publishing at top venues like NeurIPS and ICASSP. Comfortable shipping C++ DSP and deployable Python ML artifacts, he blends rigorous research with hands-on engineering and technical leadership. A trained musician as well as a researcher, he uniquely bridges musical intuition and generative audio model expertise to build creator-focused GenAI tools. Notably, his work spans text-to-audio, voice AI, and speech restoration—areas where he has delivered both disruptive prototypes and production integrations.
9 years of coding experience
13 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Electrical Engineering, Doctor of Philosophy (Ph.D.), Electrical Engineering at Tufts University