About

I build software that makes proteomics research faster and more accessible. As lead developer of NULISA Analysis Software (NAS), I've created a platform used by 100+ researchers to analyze sequencing-based proteomics data.

My background in Industrial Engineering, Data Science, and Executive Data Analysis gives me a unique perspective. I understand how to build systems that are not just technically sound, but also operationally efficient and aligned with business goals.

I work across the full stack: R Shiny front-ends, Docker deployments, SQL databases, and proteomics analysis pipelines. I build modular systems that solve current problems while staying flexible enough to evolve with new requirements.

Foundation in systems optimization, process improvement, and quantitative analysis.

Advanced statistical methods, machine learning, and computational analysis. Developed MSstats Sample Size Shiny application for proteomics experimental design during this program.

Strategic approaches to data-driven decision making and analytics leadership.

Leading development of NULISA Analysis Software (NAS), a modular R Shiny application for proteomics data analysis. Building scalable solutions and contributing to the NULISAseqR package.

• Lead developer of NAS - an analysis platform with modular architecture
• Designed and implemented Docker containerization with Azure Kubernetes Service deployment
• Manage CI/CD pipeline including Kubernetes manifests, automated testing, and Azure Container Registry
• Integrated testthat unit tests as deployment gates with renv environment management
• Built multi-plate merging pipeline and ETL infrastructure for NULISAseqR package, adding project-level analysis capabilities that didn't exist before
• Created automated QC systems and visualization dashboards

Provided statistical analysis support for clinical studies while developing Shiny applications that helped bench scientists visualize and analyze proteomics data independently. Worked with mass spectrometry-based proteomics and single-cell RNA sequencing (scRNAseq) datasets.

• Supported statistical analysis for multiple clinical studies
• Developed Shiny applications that let bench scientists visualize proteomics data without coding
• Built tools for basic statistical analysis accessible to non-statisticians
• Worked with challenging datasets including mass spec proteomics and scRNAseq data
• Proposed out-of-the-box solutions and built toolbox of statistical methods
• Made complex statistical methods accessible through user-friendly interfaces

Completed two co-op rotations with the Energy Markets Team, developing analytical tools and web applications for demand response program operations. Worked with geographically distributed teams across new and old energy markets.

• Designed mission-critical improvement to settlement process involving UI development and database management
• Developed UTI web application for inspecting and identifying interval meter data
• Built analytical tools for enrollment, nomination, and settlement processes
• Created R-Shiny dashboards for monitoring customer participation in Demand Response programs
• Resulted in dramatic increase in efficiency of key operational processes
• Collaborated with cross-functional, geographically distributed teams