Peter Plantinga
Postdoctoral Researcher at McGill University
Montreal, Quebec, Canada
Summary
🤩
Rockstar🎓
Top SchoolPeter Plantinga is a machine learning researcher and engineer with 13 years of experience specializing in speech and audio processing, currently a postdoctoral researcher at McGill after completing a PhD in Computer Science at The Ohio State University. He has bridged academia and industry roles—including research at Mila and applied AI leadership at JPMorgan Chase—delivering both foundational toolkits and production ML solutions. Notably, he contributed significant architecture and modularization work to the widely used SpeechBrain toolkit (introducing a flexible Nerve class and refactored CRDNN model), reflecting deep expertise in PyTorch-based speech systems. Comfortable moving between research, software engineering, and team leadership, he seeks full-time roles that combine novel research with production-grade implementation.
13 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy (PhD), Computer Science, Doctor of Philosophy (PhD), Computer Science at The Ohio State UniversityBachelor of Computer Science, Computer Science, Bachelor of Computer Science, Computer Science at Calvin College
English, American Sign Language
Stackoverflow
451reputation
13kreached
8answers
1question
Github Skills (19)
pytorch10
modeler10
modello10
deep-learning10
neural-network10
modular-programming10
speech-recognition10
modeling10
speech-processing9
asr8
html6
lstm6
tensorflow6
css6
machine-learning6
Programming languages (7)
Github contributions (5)
speechbrain/speechbrain
Feb 2020 - Sep 2022
A PyTorch-based Speech Toolkit
Role in this project:
ML Engineer
ML EngineerContributions:186 reviews, 793 commits, 85 PRs in 2 years 7 months
Contributions summary:Peter's commits primarily involve the implementation of a new `Nerve` class and refactoring of the `CRDNN` model in the SpeechBrain toolkit. They introduced an important structure with shortcut connections to enable the flexible and efficient design of deep learning architectures. The changes suggest an active role in enhancing the toolkit's capabilities by providing new methods for modular neural network construction and integrating them into existing models.
voice-recognitionasrspeech-recognitionspeech-separationspeaker-verification
OSU-slatelab/actor_critic_specmap
Sep 2017 - May 2018
Contributions:1 release, 67 commits, 36 pushes 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.