Research Fellow (working On Artificial General Intelligence Safety) at Astera Institute
Massachusetts, United States
Join Prog.AI to see contacts
Join Prog.AI to see contacts
Summary
👤
Senior
🎓
Top School
Steven Byrnes is a physicist-turned-AGI safety researcher with 14 years of experience bridging applied physics, neuroscience, and machine learning to tackle how future brain-like AIs can be trained to be compassionate rather than indifferent. Currently a Research Fellow at the Astera Institute, he studies connections between reinforcement learning reward functions and innate drives in neuroscience, pursuing technically rigorous solutions to value alignment. His background includes inventing precision sensors and algorithms at Draper—spanning atomic clocks, LIDAR-on-a-chip, and Bayesian/ML-Kalman fusion—and postdoctoral work in optics at Harvard, giving him a rare mix of experimental, theoretical, and systems-level skill. An active open-source contributor, he has improved front-end UX and documentation for the Crafty JS game engine, reflecting a practical attention to usability and developer experience. Based in Massachusetts, he combines deep academic training (PhD Berkeley) with hands-on engineering instincts and a focus on problems that are both scientifically subtle and societally consequential.
13 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy Physics, Doctor of Philosophy Physics at University of California, Berkeley
High School Diploma, High School Diploma at The Roxbury Latin School
Bachelor of Arts, Bachelor of Arts at Harvard University
Contributions summary:Steven primarily contributed to the JavaScript game engine by improving the user interface and documentation. They implemented examples within sprite documentation to aid developers. The user also addressed UI issues by fixing bugs related to the DOM and text rendering, ensuring proper text styling and cursor behavior. Furthermore, the user refactored draggable code to be more memory-efficient and easier to read.
transfer-matrix method for optics of thin and thick multilayer films
Contributions:42 commits, 4 PRs, 25 pushes in 10 years 1 month
opticsmethodmultilayerthintransfer-matrix-method
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.