Chris Kirmse is a seasoned software engineer in the San Francisco Bay Area with 11 years building fast-moving game and internet products at growth-stage companies. He thrives on rapid product development, balancing infrastructure and feature trade-offs while leading small teams to deliver polished user experiences. Comfortable across Windows and Unix/Linux and a wide language set—from C/C++ and Objective-C to Perl, PHP, Python, shell scripting, and modern Node.js/JavaScript—he treats each new company as a technical adventure. Chris also contributes to open-source ML tooling, including improvements to a popular attention-based OCR project, showing a pragmatic curiosity that spans from systems to machine learning. He’s equally likely to seed a product idea during a nerf basketball break as in a deep design discussion, blending creativity with engineering discipline.
A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.
Role in this project:
ML Engineer
Contributions:18 commits, 13 PRs, 32 comments in 1 month
Contributions summary:Chris primarily contributed to the `attention-ocr` project by implementing and refining features related to text recognition using a CNN and seq2seq model. Their work focused on improving compatibility with different Python versions, fixing dataset issues, and adding functionality for full ASCII character support. They also addressed performance issues by modifying the CNN architecture and implemented the ability to make predictions from loaded checkpoints, enhancing the usability of the OCR model.
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.