Experience in research design and time series analysis using large datasets with a mixture of human behavior and physiology. I currently work at Senseye, Inc as a Staff Research Scientist, where I work closely with Clinical and Machine Learning Teams to provide mental health diagnostics using ocular, voice, and performance based metrics. While obtaining a PhD in Neuroscience, I measured time series fMRI data to understand the neural mechanisms by which continuous experience gets transformed into discrete episodic events. Organizing and performing quality assessment of time series ocular data.• Created and manage complex database from PTSD diagnostic app. Automatically process, clean and organize incoming data from disparate sources, e.g., event-related app data, survey data, computer-vision (CV) output from face video files, into a single easily accessible and reproducible database. Organization includes quality assessment flags to assess ground-truth validity and reliability of ocular signals from CV algorithms and communication flags with the Clinical Team and CV Engineers. I manage the repository under version control (git).Experimental design for PTSD diagnostic app.• Designed app stimuli to maximize separability in ocular signals across mental health diagnoses. Culling literature for theory-based explanations driving group differences in ocular metrics. Generate analytic reports and transform statistical metrics for delivery to Machine Learning (ML) Team, in addition to performing Diagnostic Classification in conjunction ML. Present results at conferences. Methods: mixed effect modeling, theory-based literature curation. The mechanism of organizing continuous experience• I designed and analyzed a series of experiments using naturalistic continuous event sequences (i.e., movies) and structured event sequences (i.e., word lists) to understand mechanisms of memory differences in young children and adults. Methods: mixed effect modeling, permutation-based analyses, bootstrapping, and probability-based analyses.How reactivating the past affects memory for the future• Using brain imaging data and machine learning I built models to predicted participant’s thought processes as they performed memory tasks. I created and optimized a data processing pipelines for large dataset (~300 GBs in total) to understand how spatially distributed neural regions interact to facilitate memory.