Max Hodak

Software Engineer at sciencecorp

San Francisco, California, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Max Hodak is a software engineer with 16 years of experience who blends biomedical engineering training from Duke with hands-on work building tools for scientists. He began in neurophysiology labs developing brain–machine interface experiments and later founded MyFit, a college-student matching startup that exited to Naviance after a Silicon Valley detour. At Transcriptic he focuses on developer-facing products that accelerate laboratory automation and scientific workflows. His open-source work includes an autoencoder for continuous molecular representations, reflecting an interest in applied ML for chemistry and biology. Based in San Francisco and self-styled a "reality engineer," he bridges experimental science, ML modeling, and practical product engineering.
code16 years of coding experience
bookBSE, Biomedical Engineering, BSE, Biomedical Engineering at Duke University
github-logo-circle

Github Skills (14)

keras10
machine-learning10
deep-learning10
python10
autoencoder10
modeling9
tensorflow9
trainings9
data-preprocessing9
visualization8
data-visualization8
data-visualisation8
data-visualizations8
visualizations8

Programming languages (7)

TypeScriptShellC++CJavaScriptRubyPython

Github contributions (5)

github-logo-circle
maxhodak/keras-molecules

Oct 2016 - Jan 2017

Autoencoder network for learning a continuous representation of molecular structures.
Role in this project:
userML Engineer
Contributions:24 commits, 16 PRs, 40 pushes in 2 months
Contributions summary:Max focused on developing and improving a molecular autoencoder network for learning a continuous representation of molecular structures. Their contributions involved visualizing the model, refining the projection of the latent space, and implementing decoder functionality. They also worked on the preprocessing scripts and updated the model architecture, adding activations and refactoring components.
representationautoencoderautoencodersmolecular-structuresdeep-learning
maxhodak/notes

Apr 2010 - Oct 2017

Contributions:36 commits, 21 pushes, 3 branches in 7 years 7 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.
Request Free Trial
Max Hodak - Software Engineer at sciencecorp