Resume

[Download as pdf]

Professional Experience

Mindstrong Health
2020-present
Senior Data Scientist

  • Built and deployed machine learning models to help our clinical team provide therapeutic and psychiatric services to under-served populations
  • Estimated clinically-meaningful quantities (sleep, physical activity) from passively-collected phone data using approaches adapted from the biometric research literature
  • Helped junior members of the team deploy their models at scale, promoting a culture of collaboration and best programming practices throughout the data organization

KeepTruckin
2019-2020
Data Scientist

  • Designed, validated, and deployed ML models on massive datasets created from our fleet of 200,000+ IoT devices
  • Conducted experiments and ran statistical tests to help understand our users’ behavior patterns and measure product engagement
  • Analyzed the feasibility of new product offerings and delivered my findings to the executive team, quantifying the potential financial impacts on our own business and on our customers’

Bayes Impact / Ovio
2017-2019
Data Scientist

  • Led the research arm of the organization, investigating disparities in access to location-based social services
  • Designed and implemented models, algorithms, and APIs to support in-house initiatives to bring evidence-based decision making to government policymaking at federal, state, and local levels
  • Worked in partnership with the Centers for Medicare & Medicaid Services to measure physician quality from a massive claims data warehouse as part of a congressionally-mandated effort to provide financial incentives for value-based care

MedeAnalytics
2014-2016
Data Engineer

  • Developed two web applications (and underlying databases to support them) for a large state Medicaid agency:
    1. A big-picture analytics dashboard tracking important public health issues and agency costs
    2. A portal for health professionals to view patients' health information at the point of care
  • Overhauled the end-to-end ETL process for Medicaid claims to dramatically reduce latency in data availability

University of Wisconsin-Madison
2012-2014
Teaching Assistant

  • Taught calculus for scientists and engineers to over 200 undergraduate students over two years
  • Designed original course content to engage students. (Ask me about my favorite Lagrange multiplier example!)

Education

2014 Masters of Arts, Mathematics, UNIVERSITY of WISCONSIN–MADISON

2012 Bachelors of Science, Mathematics, STANFORD UNIVERSITY


Professional Development

2016 Data Science Immersive, GALVANIZE ACADEMY


Awards

2014 Mathematics Graduate Teaching Award, UNIVERSITY of WISCONSIN–MADISON

2012 Phi Beta Kappa Inductee, STANFORD UNIVERSITY


Technical Skills

LANGUAGES

  • Python, Java, C++
  • Spark (PySpark and Spark SQL)
  • SQL (Snowflake, Redshift, Vertica, Postgres, Hive) and NoSQL (MongoDB, DynamoDB)

MACHINE LEARNING & STATISTICS

  • pandas, numpy, scikit-learn, statsmodels, scipy, seaborn
  • SparkML, XGBoost, PyTorch, BERT via 🤗 transformers
  • regression, classification, clustering, hyper-parameter tuning, feature selection
  • hypothesis testing, bootstrapping, cross-validation, Bayesian inference
  • statistical data analysis and causal inference

MISCELLANEOUS

  • AWS ecosystem, Docker, Kubernetes
  • GIS and spatial algorithms, mapping and data visualization (Looker, Tableau, Redash)
  • Data modeling, API design, high-performance Python, web-scraping, multiprocessing