Hudson Cooper
Principal Applied Scientist at Microsoft
Los Angeles, California, United States
Summary
🤩
Rockstar🎓
Top SchoolHudson Cooper is a Principal Applied Scientist in Los Angeles with nine years of experience building and shipping production-grade generative AI systems, currently working on Guidance at Microsoft to enable constrained decoding of large language models. He holds an M.Sc. in Complex Systems Modelling from King’s College London and a B.S. in Probability and Statistics with an ML focus from UC San Diego, grounding his work in rigorous probabilistic and systems thinking. Hudson’s research centers on parameter-efficient fine-tuning, model interpretability and introspection, and safely integrating traditional software with GenAI for mission-critical applications. He has led AI teams and products from director to principal engineer roles across startups and research labs, translating research insights into robust, deployable systems. An active contributor to the guidance-ai project, he has implemented core grammar and JSON schema handling features that improve schema-heavy prompt control and recursion behavior. Colleagues describe him as a pragmatic researcher who blends theoretical depth with hands-on backend engineering to make complex models controllable and auditable.
9 years of coding experience
8 years of employment as a software developer
University of California, San Diego4.0, 4.0 at Soquel High SchoolM.Sc., Complex Systems Modelling, M.Sc., Complex Systems Modelling at King's College London
Stackoverflow
75reputation
8kreached
1answer
4questions
Github Skills (17)
parser10
python10
json-schema10
parsing10
parse10
regular-expression9
api7
apidoc7
html6
libsvm6
quadratic-programming6
liblinear6
dictionary6
svm6
html5-canvas6
Programming languages (4)
Github contributions (5)
guidance-ai/guidance
Jul 2023 - Mar 2025
A guidance language for controlling large language models.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:205 reviews, 138 PRs, 64 pushes in 1 year 8 months
Contributions summary:Hudson primarily contributed to the `guidance-ai/guidance` repository by implementing features related to the underlying grammar and JSON schema handling. They worked on modifying the guidance wrapper to pop the first argument and fix incorrect behaviors in the `_json_schema_to_grammar` module for schemas with numerous properties. The user also addressed issues related to recursion and implemented features for enum support and handling of additional properties.
hudson-ai/.dotfiles
Jul 2019 - Nov 2024
Contributions:33 pushes, 3 branches in 5 years 5 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.