Bio


I am a Research Software Engineer (RSE) | Data Scientist & Data Manager at the Stanford Translational AI (STAI) Lab. I lead data engineering and AI infrastructure across large-scale neuroscience and healthcare projects, building standards-first, end-to-end pipelines for data collection, curation, preprocessing, and multimodal integration. My work emphasizes reproducibility, scalability, and interoperability through BIDS-style schemas, schema validation, containerized deployments, and CI/CD across heterogeneous computing environments.

I have designed and maintained containerized preprocessing workflows for thousands of subjects across major datasets, automating modality-specific steps such as registration, intensity normalization, bias-field correction, motion/confound estimation, quality control, and downstream metadata exports. I ensure these pipelines are robust, well-documented, versioned, and reusable across projects, sites, and modalities.