Why: Want to help explore our universe? Every day at JPL we interact with data from 22 spacecraft around our solar system and dozens of projects in development. As data generation from these projects grows, so does our need for distributed data storage, efficient analysis and novel visualizations. We think empowering our center with applied big data and data science helps us find the right questions - and then the right answers to understand the world around us.
What: This summer we're bringing 5-10 curious data hackers (CS, ML, Stats, Econ, Analytics etc) to JPL to apply data science to a variety of problems. In teams of 2-3, we'll work with our engineering squad to implement projects that you'll help define, like:
- Architecting data pipelines for next-gen spacecraft
- Integrating systems with distributed data stores clusters in the cloud
- Clustering spacecraft and support anomalies
- Predicting system performance
- Classifying science telemetry
We're fans of Hadoop, Hive, Mahout, Weka, Splunk, d3, python, java, node and experimenting with the right tools for the problems at hand.
When: 6/18 - 8/23
How: Individual or teams of 2 students can apply by sending your github username, a link to a personal project or resume to joinbigdata@jpl.nasa.gov