Ashwin Raaghav
Data Scientist
Munich, Bavaria, Germany
Summary
🤩
Rockstar🎓
Top SchoolAshwin Raaghav is a data scientist with a decade of experience applying machine learning and MLOps to healthcare devices, clinical trials, and enterprise decision systems. Based in Munich, he has built end-to-end data infrastructures in Azure, engineered PySpark ETL pipelines, and created algorithms to monitor implants and surface anomalies for better patient and device health. His background spans research and industry—from contributing core enhancements to the SMAC3 Bayesian optimization library (adding successive halving and adaptive capping) to deploying forecasting and optimization solutions for clients at Mu Sigma. He combines strong ML research (Variational Autoencoders, self-supervised learning) with practical production skills in back-end systems and reproducible experimentation. Known for turning noisy sensor data into actionable insights, he bridges stakeholder needs and technical implementation to drive measurable impact.
10 years of coding experience
4 years of employment as a software developer
Master of Science - MSc, Computer Science, Master of Science - MSc, Computer Science at The University of FreiburgBachelor of Engineering (BE), Computer Science and Engineering, Bachelor of Engineering (BE), Computer Science and Engineering at RMK Engineering College
English, Tamil, Hindi, German
Github Skills (12)
hyperparameter-optimization10
bayesian10
automated-machine-learning10
automl10
optimisation10
python10
optimization10
configuration-file9
configurations9
configuration-management9
scikit7
scikit-learn7
Programming languages (3)
Github contributions (5)
automl/SMAC3
May 2019 - May 2020
SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:68 commits, 23 PRs, 113 pushes in 1 year
Contributions summary:Ashwin primarily contributed to the core functionalities of the SMAC3 package, focusing on the implementation of successive halving, a crucial component for hyperparameter optimization. Their work included adding successive halving with examples, integrating adaptive capping to the existing intensification method, fixing the initialization issues and addressing the bugs. The user also made changes to the base classes, such as AbstractRacer and Intensifier, to better integrate with the pull architecture.
bayesianhyperparameter-optimizationbayesian-optimizationbayesian-optimisationhyperparameter-tuning
ashraaghav/dl-lab-ss19
May 2019 - Apr 2023
Deep Learning Lab SS19, University of Freiburg
Contributions:7 pushes in 4 years
deep-learningmachine-learningtensorflowfreiburglab
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.