Research Engineer I

A Woman-Owned, Minority-Owned (Hawaiian), Veteran-Owned, Small Business, P3I provides comprehensive, cost-effective, and integrated services to the federal government, civilian agencies and departments, and the commercial business sector.

The Data Sciences Group is developing new methods to analyze heterogeneous data from a variety of sources, including engineering systems, scientific observation, and textual reports. The group applies various approaches to searching, characterizing, interpolating within, and reasoning about, very large datasets. These datasets contain many of the characteristics of Big Data (extremely large, streamed at a high frequency, contains data quality issues, and are multivariate/heterogeneous in nature). Examples of such datasets are:

* Numeric, discrete, and textual data from engineering systems such as flight, radar track, or pilot report data from the national airspace. * Images and other data from various NASA missions observing earth, other planets, and interplanetary space * Simulation Data * Environmental building recordings and systems health data collected through BACnet protocol, such as: lighting, shade, temperature, plug loads, photovoltaic sensor data, etc. The successful candidate would support the group’s goal of better organizing, extracting, and presenting relevant information buried in a variety of large real world data sets. To accomplish this, the candidate must be able to quickly understand the basic mechanisms for applying data mining methods to data sets and be able to interpret the results. The majority of this work will involve working with NASA partnerships to understand the requests and execute the appropriate data mining techniques to solve real world problems. Such problems fall under the domains of aeronautics, Earth science, and environmental systems health monitoring. In order to ensure that the findings are correct the task will also require the ability to coherently generate visualizations that summarize the findings and present them to subject matter experts for their feedback. The aim for this group is to develop useful techniques that can help aid safety and efficiency in the national airspace as well as supporting diverse data mining efforts for current and future NASA missions.

You are submitting your information for consideration to a position that is currently available under the Intelligent Systems Research & Development Services 2 (ISRDS-2) program at Ames Research Center, CA. If selected, your employment offer may be with SGT or one of our teammates on the contract.Position Requirements * Testing of new algorithms on data sets. * Familiar with data mining/big data concepts and methods. * Willing to learn new skills and data mining methods. * Programming in C/C++/Matlab/java/python. * Familiar with distributed computing architectures such as PBS Schedulers, Spark, Hadoop, MapReduce. * Excellent communication skills for multi-center and partnership activities. * Excellent references. * Linux Shell programing BASH/awk/sed/grep/UNIX commands etc. * Well organized with the mindset of ensuring that the work is validated and correct. **Other Desired Skills** * Familiar with Databases MySQL/PostgreSQL. * Web based User interface design, visualization, and development. Familiar with JSON Apache. * Knowledge of National Airspace operations and procedures. * Experience with data mining algorithms: regression, classification, clustering, anomaly detection, kernel methods, text mining.