Automated Feature Discovery & Anomaly Detection for Scientific Data Archives
Department
PPPL Computational Science
Category
Research and Laboratory
Job Type
Temporary
Overview
PPPL summer internship program participant.
A U.S. Department of Energy National Laboratory managed by Princeton University, the Princeton Plasma Physics Laboratory (PPPL) is tackling the world's toughest science and technology challenges using plasma, the fourth state of matter. With more than 70 years of history, PPPL is a leader in the science and engineering behind the development of fusion energy, a potentially limitless energy source. PPPL is also using its expertise to advance research in the areas of microelectronics, quantum sensors and devices, and sustainability sciences. Whether it be through science, engineering, technology or professional services, every team member has an opportunity to contribute to our mission and vision. Come join us!
Responsibilities
Core Duties:
- This project focuses on Unsupervised Representation Learning to automate data curation for the SURGE framework. The intern will build a pipeline using Autoencoders to extract meaningful features from high-dimensional scientific data, creating a "Latent Atlas" that autonomously tags physics regimes and identifies outliers. The work will involve training deep learning models to compress raw data into structured feature spaces required for downstream surrogate modeling.
Qualifications
Education and Experience:
- Undergraduate student.
Knowledge, Skills and Abilities:
- This project is suitable for a student with a strong interest in Deep Learning (Autoencoders/Unsupervised Learning) and Data Mining. They will be working on the "Feature Extraction" component of the SURGE ecosystem.
Working Conditions:
- On-site.
Princeton University is an Equal Opportunity and all qualified applicants will receive consideration for employment without regard to age, race, color, religion, sex, sexual orientation, gender identity or expression, national origin, disability status, protected veteran status, or any other characteristic protected by law.
Standard Weekly Hours 40.00
Eligible for Overtime Yes
Benefits Eligible No
Find Your Best Opportunity
Tell them AcademicJobs.com sent you!

