Pranav Simha
Software Engineer at Alteryx
San Diego, California, United States
Summary
🤩
Rockstar🎓
Top SchoolPranav Simha is a software engineer based in San Diego with six years of experience building AI/ML cloud products and improving developer tooling. At Alteryx he contributes to production AutoML and data-typing systems, having shipped performance improvements and data-check enhancements in EvalML and Woodwork that reduced inference runtimes and hardened time-series and ID column handling. His background includes hands-on SQA and intern roles where he delivered automated test frameworks, a Flask/PostgreSQL test-reporting dashboard, and an NLP classifier using BERT—skills that blend backend engineering, ML, and quality assurance. A Georgia Tech MS student with a BS in Computer Science from Oregon State, he combines practical open-source contributions with a focus on reliability and performance in ML pipelines. Notably, his EvalML commits tackled subtle datetime and frequency inference corner cases, showing attention to data hygiene that prevents downstream model failures.
6 years of coding experience
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at Georgia Institute of TechnologyBachelor's degree, Computer Science, Bachelor's degree, Computer Science at Oregon State University
Github Skills (9)
pandas10
machine-learning10
feature-engineering10
data-validation10
python10
data-science10
pytest9
hyperparameter-tuning8
automl8
Programming languages (3)
Github contributions (5)
alteryx/evalml
Jul 2022 - Sep 2022
EvalML is an AutoML library written in python.
Role in this project:
ML Engineer
ML EngineerContributions:11 reviews, 6 commits, 12 PRs in 1 month
Contributions summary:Pranav implemented changes to the `EvalML` library related to data checks and time series regularization. These modifications involved adjusting thresholds and window sizes, specifically in the context of datetime format validation and frequency inference. The commits also included updates to data check actions, primarily for identifying and handling ID columns, ensuring the first column is flagged as the primary key when appropriate. Furthermore, the user updated data check error codes for regression problems involving unsupported data types.
pythondata-sciencemodel-selectionoptimizationmachine-learning
broku13/CS362-W2020
Jan 2020 - Feb 2020
OSU, CS362, Software Engineering II, Repository for Winter 2020
Contributions:11 pushes, 8 branches in 1 month
javawinterengineeringosu
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.