Menoua Keshishian
Machine Learning Engineer at Neuralink
San Francisco, California, United States
Summary
👤
Senior🎓
Top SchoolMenoua Keshishian is a machine learning engineer and PhD candidate in Electrical Engineering at Columbia University with eight years of experience applying linear and deep learning to model how speech and spoken language are processed in the human brain. Her work spans academic research—where she used linear and nonlinear ML to reveal auditory cortex mechanisms—to industry roles building BCI applications and leading ML efforts at Wispr Flow and Neuralink. She combines expertise in supervised, unsupervised, and self-supervised speech and language modeling with hands-on experience deploying models for brain–computer interfacing. Based in San Francisco, she bridges neuroscience and production ML, bringing a research-first mindset to product-focused engineering. An uncommon strength is her background in both sparse/low-dimensional modeling and quantum computing coursework, which informs creative approaches to high-dimensional neural data.
8 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD Electrical Engineering, Doctor of Philosophy - PhD Electrical Engineering at Columbia UniversityBachelor of Science (B.Sc.) Electrical Engineering, Bachelor of Science (B.Sc.) Electrical Engineering at Sharif University of Technology
English, Armenian, Persian
Github Skills (24)
receptive-field10
corona10
widgets10
elm10
climate-change10
user-interface9
neuroscience9
serve9
rust9
python8
neovim-plugin8
lua8
latency8
neovim8
toolbox7
Programming languages (3)
Github contributions (5)
menoua/cog-task
Aug 2022 - Nov 2022
CogTask: A general-purpose low-latency tool for designing cognitive tasks.
Contributions:313 commits, 4 PRs, 219 pushes in 2 months
latencyservecognitivepurposegeneral-purpose
naplab/DSTRF
May 2020 - Jun 2022
Dynamic Spectrotemporal Receptive Field (dSTRF) Analysis Toolbox
Contributions:1 release, 32 commits, 1 PR in 2 years 1 month
neurosciencedeep-learningtoolboxmodel-analysisneural-network
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.