Looking for a job

Belay Gebregergis

@belaygebregergis

Message

I build reproducible machine learning pipelines for biomedical discovery and biomarker validation.

Canada

Message

What I'm looking for

I'm looking to apply machine learning, statistical analysis, and reproducible data pipelines to complex biomedical or health-related datasets, owning projects end to end while collaborating with distributed, cross-functional teams.

At the TANZ Centre for Research in Neurodegenerative Diseases at the University of Toronto, I apply large language models and graph neural networks to structural and multi-omics datasets to identify therapeutic targets and disease-relevant patterns.

I've built reproducible Python, R, SQL, and MATLAB pipelines for large longitudinal biomedical datasets and developed a pre-registered, multi-cohort biomarker validation framework adapted from FDA-NIH BEST principles. My work defines rigorous quality thresholds to test whether findings generalize across independent patient cohorts.

My background spans neurodegeneration, electrophysiology, synaptic biology, pharmacology, and toxicology, including research roles in Canada, Germany, France, and Ethiopia. I communicate complex findings through publications, grants, and scientific presentations while owning multi-stage projects from design through dissemination.

Experience

Work history, roles, and key accomplishments

Current

Postdoctoral Fellow

Current

University of Toronto

Mar 2026 - Present (6 months)

Apply large language models and graph neural networks to structural and multi-omics biomedical datasets to identify novel therapeutic targets and disease-relevant patterns. Designed and open-sourced a machine learning evaluation toolkit assessing the reliability of EEG-derived biomarkers, defining precise quality and acceptance criteria for measures intended to generalize across independent patien