I'm a Data Scientist at Microsoft with a Ph.D. in Applied Mathematics from NC State University. My research sits at the intersection of probabilistic machine learning, uncertainty quantification, and scientific computing: from developing Gaussian process models for clinical labor prediction to calibrating physiologically-based pharmacokinetic models with Bayesian surrogates.
| Area | Focus |
|---|---|
| Gaussian Processes | Sparse GP regression, multi-output kernels, clinical prediction |
| Uncertainty Quantification | Bayesian MCMC, polynomial chaos, Morris sensitivity screening |
| Physics-Informed NNs | PDE-residual learning for boundary layer fluid dynamics |
| Pharmacokinetics | GP surrogates for physiologically-based PK model calibration |
| Demand Forecasting | Time-invariant methods and special event detection at scale |
Languages
ML & Scientific Computing
Platforms & Tools
Ph.D. in Applied Mathematics, North Carolina State University
Research: uncertainty quantification, Bayesian inference, computational modeling of physical and biological systems