At Natera, I built Python and SQL pipelines for sequencing datasets ranging from research cohorts to 100K+ commercial samples, reducing manual data curation and speeding study execution.
I led analysis for the Signatera assay transition to NovaSeq, designing validation studies and defining QC thresholds to inform production readiness and deployment decisions. I also evaluated statistical models and developed QC frameworks for multiple assay components.
At Wühr Lab, Princeton University, I built Python pipelines for proteomics data and developed predictive models of protein diffusion. My hypothesis-driven analyses contributed to three publications and supported experimental research.
I have a PhD in Molecular Biology from Princeton University and experience in statistical modeling, experimentation, and genomics. I’ve also completed workshops in machine learning and generative AI, applying LLM-based tools to improve analytical workflows and documentation.
