João Sedoc
Assistant Professor at NYU Stern School of Business
New York, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolJoão Sedoc is an Assistant Professor at NYU Stern with 11 years of experience at the intersection of conversational agents and natural language processing, bringing academic rigor and applied research to industry-scale problems. He holds a PhD from the University of Pennsylvania and has blended roles in academia and industry, including research positions at Johns Hopkins and an applied research internship at Amazon. Earlier in his career he worked extensively in quantitative finance and high-frequency research, giving him a rare combination of ML/NLP expertise and production-focused quantitative engineering. An active back-end contributor to the well-known KenLM language-modeling library, he implemented vocabulary merging and indexing features with thorough unit tests—demonstrating both systems-level coding skill and attention to reproducibility. Based in New York, he balances theoretical work on conversational agents with practical implementations that scale to real-world language systems.
11 years of coding experience
14 years of employment as a software developer
Doctor of Philosophy (PhD), Doctor of Philosophy (PhD) at University of Pennsylvania
Github Skills (13)
algorithm10
data-structures10
algorithms10
c-language10
cprogramming-language10
language-modeling10
data-structure10
boost9
unit-testing8
file-processing8
file-handling8
fileio8
file-access8
Programming languages (11)
Github contributions (5)
kpu/kenlm
May 2015 - May 2015
KenLM: Faster and Smaller Language Model Queries
Role in this project:
Back-end Developer
Back-end DeveloperContributions:12 commits, 12 pushes, 1 comment in 17 days
Contributions summary:João primarily contributed to the implementation of a vocabulary merging and indexing mechanism within the KenLM library. They focused on the `lm/interpolate` directory, creating and modifying files related to merging vocabulary from multiple language models into a universal vocabulary. The contributions involved the use of priority queues, hash maps, and file reading operations. Unit tests were also added to validate the functionality.
kenlmlanguage-model
dialog-systems-class/dialog-systems-class.github.io
Jan 2017 - Jan 2021
Contributions:1 release, 1 PR, 133 pushes in 4 years 1 month
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.