Visiting Student - MCS - Jiang, Bo - 9.21.26.

Argonne National Laboratory • Lemont, IL

1d • Onsite

About The Position

Scientific datasets exhibit diverse characteristics, and lossy compressors expose numerous algorithmic parameters whose optimal settings vary substantially across datasets, applications, and user requirements. Manually identifying suitable compressors and configurations is time-consuming and often requires extensive domain and compression expertise. This project aims to develop an agentic system that automatically selects and configures lossy compression methods according to user-specified quantities of interest (QoIs). The system will characterize input data, explore candidate compressors and parameter settings, evaluate their effects on application-relevant QoI metrics, and iteratively refine its decisions to identify configurations that satisfy user-defined accuracy constraints while optimizing compression ratio, throughput, or other performance objectives. By integrating data analysis, automated experimentation, QoI evaluation, and adaptive decision-making into a unified workflow, the proposed system will make scientific lossy compression more accessible, efficient, and reliable across diverse datasets and applications.

Requirements

• Must be 18 years or older at the time the appointment begins.
• Currently enrolled in undergraduate or graduate studies at an accredited institution.
• Graduated from an accredited institution within the past 3 months; or
• Actively enrolled in a graduate program at an accredited institution.
• The entirety of the appointment must be conducted within the United States.

Responsibilities

• Characterize input data
• Explore candidate compressors and parameter settings
• Evaluate the effects of compressor settings on application-relevant QoI metrics
• Iteratively refine decisions to identify configurations that satisfy user-defined accuracy constraints while optimizing compression ratio, throughput, or other performance objectives

What This Job Offers

• Job Type: Part-time
• Career Level: Entry Level
• Education Level: No Education Listed