Guy Gur-ari is a research scientist in AI with 12 years of engineering experience, currently based in Palo Alto and co-founder at Augment after a stint at Google. He blends practical systems engineering with AI research, notably contributing backend improvements to the high-profile BIG-bench benchmark by enabling efficient batched model evaluation. Guy excels at turning research ideas into robust, scalable code—optimizing APIs and test suites to support real-world model workloads. His background reflects both startup grit and large-scale engineering discipline, making him equally comfortable prototyping new models and productionizing them. An understated strength is his focus on developer ergonomics, simplifying interfaces so teams can iterate faster.
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
Role in this project:
Back-end Developer
Contributions:153 reviews, 354 commits, 83 PRs in 1 year 10 months
Contributions summary:Guy made several contributions to the task API, improving the efficiency of model functions by allowing them to accept batched inputs. Their work involved modifying the `bigbench/api/task.py` and `bigbench/api/json_task.py` files to support batch processing. In addition, the user made updates to the unit tests and corrected the calls to API functions.
Numerical simulation of the Sachdev-Ye-Kitaev fermion model
Contributions:4 commits, 3 pushes, 1 branch in 1 year 4 months
numerical-simulationkitaevsimulation
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.
Request Free Trial
Guy Gur-ari - Research Scientist in AI at Stealth Startup