Summary
Mahdi Baghbanzadeh is an AI Engineer and PhD candidate in Health and Biomedical Data Science with eight years of hands-on experience applying machine learning, statistical modeling, and NLP to health and commercial problems. He develops and fine-tunes foundation language models for DNA sequences using PyTorch, transformers, and HPC, and has built a Python package for sequence-based predictive modeling that is published on PyPI and under review academically. His background spans end-to-end data work—from SQL and large-scale health record analysis to deploying models and teaching high-performance and cloud computing—bringing both research rigor and production sensibility. Previously he delivered measurable business impact through forecasting and segmentation (e.g., reducing incentive costs by 15% at Snapp!) and built BI tooling in R and Power BI to streamline reporting. Comfortable in academic and industry settings, he bridges computational biology and applied ML while mentoring students and contributing reproducible tools. He is based in the United States and combines deep statistical training with practical experience tuning large models on real-world sequence and health datasets.
8 years of coding experience
8 years of employment as a software developer
Master's degree Mathematical Statistics and Probability, Master's degree Mathematical Statistics and Probability at Shiraz University
Doctor of Philosophy - PhD Health and Biomedical Data Science, Doctor of Philosophy - PhD Health and Biomedical Data Science at The George Washington University
Bachelor's degree Statistics, Bachelor's degree Statistics at Shahid Beheshti University
English, Persian