Pavan Seshadri
Member Of Technical Staff at Skyfall AI
New York City Metropolitan Area United States
Summary
👤
Senior🎓
Top SchoolPavan Seshadri is a Member of Technical Staff and ML researcher with 8 years of experience building audio, speech, music, and language systems that make computers listen, read, and create. He blends academic rigor from Georgia Tech—where he published on contrastive learning for music performance and presented urban audio sensing at ICASSP—with production ML engineering experience at Amazon and startups like Moises.ai and Music.AI. His recent work spans RL+LLM world models and long-term planning as well as self-supervised music transcription, showing a knack for bridging foundational research and applied systems. Comfortable across recommender systems, speech, and NLP, he ships end-to-end infrastructure and models at scale. Beyond publications and production code, he has hands-on experience curating novel audio/video datasets for real-world sensing problems. Based in the NYC area, he combines interdisciplinary music-technology training with pragmatic ML engineering to tackle challenging audio-language problems.
8 years of coding experience
4 years of employment as a software developer
Master of Science - MS, Music Technology, Master of Science - MS, Music Technology at Georgia Institute of TechnologyNorthview High School
Github Skills (8)
tuner4
fft3
mobile-application1
ux-design1
recipe1
react-native1
district1
capstone1
Programming languages (2)
Github contributions (5)
pseshadri9/pseshadri9.github.io
Aug 2020 - Sep 2024
Contributions:43 pushes in 4 years 1 month
pseshadri9/contrastive-music-performance-assessment
Mar 2021 - Nov 2021
Contributions:19 commits, 16 pushes, 2 branches in 8 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.