• first engineer

• worked on full stack across the company's technologies and products

• set up first iterations of compute infra, dev processes

• designed schema, data model, and APIs for products

• designed, implemented early prototypes, and iterated to maturity for search, data ingestion, data pipelines, predictions, visualization, quality assessment features

• Developed and productionized bfx pipelines for processing WGS data

• Collaborated w/ assay scientists on study design, data capture, and analysis

• Built data pipelines to extract features and feed into classification / regression models

• Trained classification / regression (including custom DL) models across millions of features and thousands of data points; analyzed results, underperforming subsets of data; communicated results to a large data science group

• Contributed to ML infrastructure

• Presented work at conferences; contributed to publications; co-authored several patents in ML/DL

Detect cancer early when it can be cured

Using PacBio long read technology for rapid and accurate diagnosis of viral and bacterial infectious diseases. Data analysis of experimental results, product performance modeling, algorithm development.