Previously: Lilly · Poseida Therapeutics · Becton Dickinson · Resilience
Current: AstraZeneca

With 12+ years of experience across biotech startups and global pharma, I specialize in data science, process development, manufacturing, and CMC strategy for biologics and cell therapies. I have led technical initiatives spanning from R&D to GMP clinical and commercial manufacturing, from process development through successful regulatory submissions, with deep experience translating complex data into regulatory-ready CMC strategy.

I bring years of hands-on experience in computational and analytical pipeline development, including next-generation sequencing (NGS) data processing, QC, and analysis workflows supporting cell therapy R&D and manufacturing. This includes designing and maintaining scalable data pipelines, integrating assay, sequencing, and manufacturing data, and applying statistical and computational methods to drive process understanding, comparability assessments, and decision-making.

I also have extensive experience implementing digital and data systems across R&D and manufacturing environments, including cloud platforms, data infrastructures, and advanced analytics, leveraging tools such as AWS, Azure, Databricks, Snowflake, R, Python, and modern data visualization and business intelligence platforms. As a bioprocess engineer and data scientist, I combine technical rigor with computational and digital innovation to strengthen manufacturing strategies and accelerate the delivery of transformative therapies.

Current

Principal Engineer, Data Science — Cell Therapy Development & Operations (AstraZeneca) · Sep 2024 – Present
See full career timeline →

What I do

I work at the intersection of data science, process engineering, and CMC to help development and manufacturing teams make defensible decisions with imperfect data. My focus is translating experimental and manufacturing signals into analyses and narratives that stand up to regulatory scrutiny and materially influence program direction.

In practice, that means designing appropriate statistical frameworks, building scalable and reproducible data workflows, and communicating results clearly to cross-functional teams and regulators.

Selected highlights

• Led process data science and statistical strategy for late-stage cell therapy programs, including multiple FDA-accepted comparability assessments, supporting IND amendments and regulatory submissions.
• Designed and applied statistical frameworks tailored to cell therapy manufacturing constraints, including variance decomposition to quantify donor-to-donor variability and enable confident decision-making under small-sample conditions.
• Built end-to-end analytics workflows spanning experimental data ingestion, manufacturing data integration, and downstream analysis using Python, R, SQL, Snowflake, Databricks, and AWS, improving consistency and visibility across programs.
• Served as Product Owner and Senior Data Scientist for the development of next-generation NGS and cloud based bioinformatics pipelines, leading cross-functional R&D teams to the successful development of multiple bulk and single-cell NGS assays.
• Provided technical leadership in commercial biologics manufacturing, including oversight of outsourced GMP drug substance production, CDMO management, process monitoring, validation readiness, and execution of change controls for high-volume, revenue-critical products.

Projects & Writing

I write occasionally about applied analytics, manufacturing data strategy, and other topics I find interesting, including work at the intersection of data, decision-making, and complex systems. See my writing for examples.