Scott Purdy - Staff Engineer at Zoox

Scott Purdy

Staff Engineer at Zoox

San Francisco, California, United States

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Scott Purdy is a Staff Engineer in San Francisco with 15 years of experience building perception, sensor fusion, and tracking systems for autonomous vehicles at Zoox and Cruise. He combines deep research roots at Numenta—where he contributed to core HTM algorithms and the Numenta Anomaly Benchmark—with hands-on production engineering and people leadership as a former engineering manager and director. His work spans low-level C++ algorithmic improvements, serialization and performance tuning, and taking multiprocessing and anomaly-detection components from research into robust tooling. Comfortable bridging research and production, he frequently surfaces subtle numerical and serialization edge cases that improve system reliability in real-world deployments.

15 years of coding experience

11 years of employment as a software developer

Bachelor of Science (B.S.), Computer Science, Bachelor of Science (B.S.), Computer Science at Cornell University

Github Skills (20)

algorithm10

algorithms10

c-language10

anomaly-detection10

python10

machine-learning10

python-multiprocessing10

data-serialization10

data-structure10

serialization10

data-structures10

multi-process10

multiprocessing10

cprogramming-language10

pandas9

Programming languages (9)

JavaC++ShellJavaScriptGoHTMLJupyter NotebookCython

Github contributions (5)

numenta/nupic.core-legacy

Jun 2013 - Jul 2017

Implementation of core NuPIC algorithms in C++ (under construction)

Role in this project:

Back-end Developer

Contributions:8 releases, 663 commits, 362 PRs in 4 years 2 months

Contributions summary:Scott made several code changes related to the core NuPIC algorithms implemented in C++. The primary contributions involve fixing serialization issues for floating-point numbers within Cells4 and updating a function call in linear.cpp. Additionally, the user addressed code review recommendations in spatial_pooler.cpp and made changes to the handling of unlearned columns within the spatial pooler's compute function.

nupiccpp

numenta/NAB

Oct 2014 - Jul 2017

The Numenta Anomaly Benchmark

Role in this project:

Back-end Developer & Data Scientist

Contributions:29 commits, 20 PRs, 7 pushes in 2 years 8 months

Contributions summary:Scott contributed significantly to the core functionality of the Numenta Anomaly Benchmark (NAB) project. Their work involved modifying the scoring and runner modules to handle multiprocessing more efficiently and address potential interrupt issues. Additionally, the user introduced a spatial anomaly detection component to the Numenta detector, improving the model's ability to identify anomalies. They also refactored plotting functionalities.

benchmarkanomalymachine-learningnumenta

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