Ganesh Krishnan
Founder at Acucare
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolGanesh Krishnan is a founder and seasoned machine learning engineer with 11 years of experience building production ML systems and data-driven optimization for marketplace logistics. Based in San Francisco, he led foundational forecasting, supply modeling and pay systems at Instacart as a Staff MLE, translating complex problems into pragmatic, cost-aware solutions across supervised learning, RL, bandits and LLMs. Earlier roles in semiconductor and materials engineering show a strong experimental-statistics pedigree—he launched a >$40M/yr product line and drove defect reductions from single-digit percentages to under 0.01% using ML and statistical process control. An active contributor to open-source ML tooling, he added practical features to Instacart’s popular lore library (encoders, benchmarking estimators, S3 robustness and predict_proba support), reflecting a focus on maintainable, engineer-friendly ML. Now founding Acucare, he combines deep technical breadth with a track record of turning research-grade methods into reliable production outcomes.
11 years of coding experience
17 years of employment as a software developer
M.S Materials Science and Engineering, M.S Materials Science and Engineering at Georgia Institute of TechnologyIndian Institute of Technology Roorkee
Github Skills (8)
pandas10
machine-learning10
xgboost10
python10
data-engineering9
aws-s38
scikit8
scikit-learn8
Programming languages (6)
Github contributions (5)
instacart/lore
Apr 2018 - Feb 2022
Lore makes machine learning approachable for Software Engineers and maintainable for Machine Learning Researchers
Role in this project:
ML Engineer
ML EngineerContributions:1 release, 5 reviews, 114 commits in 3 years 10 months
Contributions summary:Ganesh primarily contributed to the `lore` library, focusing on machine learning and data processing capabilities. Their work includes implementing and improving OneHot encoders, adding a Naive estimator for benchmarking, and integrating compression into existing encoders. They also addressed file corruption issues in S3 uploads, indicating involvement in data storage and retrieval aspects of the project. Furthermore, they also worked on adding predict_proba methods to existing estimators.
pythondata-sciencemachine-learningresearchersgluon
ganesh-krishnan/bikeshareDemand
Dec 2015 - Apr 2016
Contributions:50 commits, 17 pushes, 1 branch in 4 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.