Big data analytics experts

Develops reference models and data science pipelines for predictive maintenance on industrial data.

Patents a system that vectorizes word meanings and retrieves information by vector similarity.

Builds enzyme function databases and genomics workflow management systems on supercomputing platforms.

Integrates data lake tables and resolves entities with few labels using machine learning.

Builds systems for capturing and querying high-frequency telemetry and mining large time series datasets.

Designs distributed graph analytics and operational data analysis for exascale supercomputers.

Develops Matrix Profile methods for anomaly detection and pattern discovery in massive time series.

Integrates molecular, genomic, proteomic and clinical datasets into multimodal models for toxicity screening.

Builds open-source platforms that analyze high-throughput behavioral time-series data from Drosophila.