Michaela Hardt
Managing Director At The Medical Data Integration Center
Germany
Summary
🤩
Rockstar🎓
Top SchoolMichaela Hardt is a seasoned software leader and ML engineer with eight years of industry experience and a PhD in Computer Science from Cornell, now serving as Managing Director of the Medical Data Integration Center at the University of Tübingen. Her career spans major tech companies—Google, Twitter, and Amazon—where she focused on clinical ML applications, search and timeline quality, and fairness and explainability in machine learning. She has contributed to high-profile open-source projects such as google/fhir and the AWS SageMaker SDK, building proof-of-concept models for clinical length-of-stay prediction and enhancing Clarify integrations for bias, explainability, and monitoring. Known for bridging research and production, she combines deep academic training with practical systems work that puts interpretability and data quality at the forefront. Based in Germany, she brings rare domain expertise at the intersection of healthcare data, ML explainability, and production-grade tooling.
8 years of coding experience
12 years of employment as a software developer
Doctor of Philosophy (PhD) Computer Science, Doctor of Philosophy (PhD) Computer Science at Cornell UniversityBachelor Computer Science, Bachelor Computer Science at Universität des Saarlandesgoetz.michaela@gmail.com, goetz.michaela@gmail.com at Carnegie Mellon University
Github Skills (20)
python10
machine-learning10
amazon-sagemaker10
tensorflow10
pytorch9
health9
aws9
explainable-artificial-intelligence9
smart-on-fhir9
ehealth9
medical9
hl7-fhir9
jupyter-notebook8
pytest8
testing8
Programming languages (4)
Github contributions (5)
aws/sagemaker-python-sdk
Nov 2020 - Jun 2021
A library for training and deploying machine learning models on Amazon SageMaker
Role in this project:
ML Engineer
ML EngineerContributions:4 reviews, 5 commits, 3 PRs in 7 months
Contributions summary:Michaela primarily contributed to the Amazon SageMaker Python SDK by enhancing the Clarify integration. This included adding support for the Clarify processor, model bias, explainability, and quality monitors. They also incorporated configurations for model scores, including the ability to specify predicted labels. The user's work extended to supporting accelerators and configuring headers for explainability features.
pytorchsagemakerdeployingmxnetpython
google/fhir
Nov 2018 - Jan 2019
FHIR Protocol Buffers
Role in this project:ML Engineer
ML EngineerContributions:6 commits in 1 month
Contributions summary:Michaela's primary contribution involves developing a proof-of-concept TensorFlow model to predict the length of stay, likely related to healthcare data. This is evident from the code differences, including modifications to a Jupyter notebook demonstrating model setup and training, as well as the inclusion of synthetic data generation. The user also contributed to the creation of utilities for generating synthetic TFRecord files for training and validation.
protocol-buffersbuffersfhirhealthcarehl7
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.