|
I am currently a data scientist in the department of predictive analytics and assistant professor of anesthesiology and critical care medicine at Johns Hopkins All Children's Hospital. I was previously a postdoctoral fellow at NASA supporting the Biological and Physical Sciences division, and prior to that I received my Ph.D. in chemical engineering and my M.S. in applied math and statistics from Johns Hopkins University.
My research interests include deep learning, generative models, manifold learning, dynamical systems, and biological systems. My work often involves the use of machine learning and data driven models to improve patient outcomes in clinical settings, but I also enjoy researching in my free time at the intersection of data science, chemical engineering, and dynamical systems.
Outside of academia and research, I enjoy playing soccer, lifting weights, playing chess, and collecting rare books.
My Skills
Frontend/Backend
- React
- HTML5 & CSS3
- Go
- Fortran
- SQL
- AWS
ML & SciComp
- Python
- PyTorch
- Jax
- CUDA
- Generative Models
- Dimensionality Reduction
Tools & Systems
- Git & GitHub
- Docker
- Kubernetes
- CI/CD Pipelines
Experience
Data Scientist
Working on machine learning applications to anesthesia and predictive analytics.
Contributed (so far) to six currently pending publications and presentations. Check back here or at my Google Scholar page once they are accepted!
NASA Postdoctoral Program Fellow
Supported the biological and physical sciences division as well as the materials and processes division, primarily focusing on computational modeling and data science methods.
Developed machine learning models to predict properties of specific materials and generate alloy compositions consistent with prescribed microscopic properties and developed code to simulate aluminum alloys undergoing welding and validated the produced data experimentally.
Visiting Data Scientist
Researched the use of dimensionality reduction methods to produce reduced-order surrogate models for microstructure evolution in alloys and composite materials.
Developed deep learning architectures and numerical methods for reduced-order modeling and uncertainty quantification of systems of interest to the DOE.
Get In Touch
I'm always open to new opportunities, collaborations, or coffee.