Summary
Amir Omidvarnia is a senior researcher with nine years of interdisciplinary experience applying ML/DL to neuroimaging, EEG and electrochemical imaging, currently leading deep learning pipelines for battery research at Forschungszentrum Jülich. He combines a strong academic pedigree—PhD in Bioengineering—with hands-on skills in Python, MATLAB, PyTorch and TensorFlow to build U-Net segmentation, GAN/diffusion-based synthetic datasets, and LLM-assisted annotation workflows that accelerate reproducible science on HPC clusters. His prior work uniquely bridges cognitive neuroscience and precision medicine, having developed time-series and connectivity analyses to predict cognitive performance and detect epileptic activity from multimodal data. Amir also teaches and supervises postgraduate students, translating complex methods into practical tools, and has a track record of improving robustness under limited labels and domain shift across domains from medical AI to battery microscopy.
9 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Bioengineering and Biomedical Engineering, Doctor of Philosophy (Ph.D.), Bioengineering and Biomedical Engineering at The University of Queensland
Amirkabir University of Technology
Master of Science (M.Sc.), Bioengineering and Biomedical Engineering, Master of Science (M.Sc.), Bioengineering and Biomedical Engineering at University of Tehran
Persian, English, German