Summary
Nan Shen is a Senior Machine Learning Engineer based in New York with 13 years of experience and a PhD in Genetics and Data Science, blending deep biomedical expertise with production ML systems. She has led end-to-end projects from novel microbiome time-series algorithms in academic research to deploying glycemic response models and RAG-driven personalized recipe systems at Viome. Currently focused on making American healthcare more acceptable at Sheer Health, she specializes in applying LLM fine-tuning, retrieval-augmented generation, and scalable AWS-based pipelines to clinical and consumer problems. Her work uniquely combines high-impact translational research (faster, more accurate microbiota clustering and discovery of bacterial cliques linked to metabolic outcomes) with demonstrated production metrics (e.g., saliva model AUC 0.99). Known for a curious, product-minded approach—“Stay Hungry, Stay Foolish”—she bridges biology, machine learning, and productization to move models from insight to real-world use.
14 years of coding experience