Data Scientist (Statistician II)

As a part of the Energy Initiative, the Energy Data Analytics Lab is developing and applying advanced data analytics tools to transform diverse energy data into insights that lead to energy system performance improvements. Below is an abbreviated job description. 

The Energy Data Analytics Lab is recruiting a data scientist to produce data analyses of complex energy data sets by applying computational tools and machine learning algorithms for analyzing data, producing written reports including journal publications, oral presentations including conference presentations, and web-based media such as interactive data visualizations.

Additionally, this position will assist with the analysis of unique data sets ranging from satellite imagery and remote sensing data, macro-economic energy market data, and building-level smart meter data. The data scientist will work on signature projects including how remotely sensed data (satellite imagery and lights at night data) can be used to provide information on energy systems infrastructure, characteristics, and resources for public policy and decision makers, as well as other researchers. This position will help develop and apply techniques for extracting information about the location and characteristics of energy infrastructure (solar photovoltaics, buildings and their associated energy consumption, transmission lines, power plants, regions of the world with access to electricity, etc.) automatically from remote sensing data using deep machine learning techniques.

Required Skills/Knowledge/Abilities

  • Proficiency in Python programming, preferably with experience using Numpy and Matplotlib.

  • Conceptual understanding of machine learning (particularly predictive modeling) including linear and nonlinear regression; classification; supervised and unsupervised learning.

  • Data processing skills including cleaning (handling missing or corrupt data), analysis (using statistical methods), and interpretation.

  • Sound understanding of probability and statistical methods and a comfort with differential and integral calculus. 

  • An independent work ethic, requiring minimal daily supervision 

  • Ability to carry out multiple projects simultaneously.

  • Exceptional organizational and project management skills, with attention to details.

  • Knowledge of or willingness to learn about energy systems including electricity generation, transmission, distribution, and power market operation and technologies; transportation systems and fuels; and consumer energy efficiency decision-making and strategies.

Desired Skills/Knowledge/Abilities

  • Deep learning (subfield of machine learning) expertise, or willingness to quickly learn Keras, Tensorflow, and running machine learning models on Graphics Processing Units (GPUs)

  • Working knowledge of command line operations and the Linux operating system.

  • Data visualization experience, including online and interactive data presentation such as D3.js, vega, or vega lite.

  • Strong writing skills, as demonstrated by the ability to clearly describe statistical models and data-oriented research results.

  • Polished verbal communication skills in presenting to both technical and non-technical audiences.

More information on the Energy Data Analytics Lab. 

For the full job description click here. To apply click here. Requisition number 401619625.

Mailing Address

Duke University Energy Initiative
Box 90467
Durham, NC 27708

Street / Delivery Address

Duke University Energy Initiative
140 Science Drive
Gross Hall, Suite 101
Durham, NC 27708

919-613-1305 

Aug
22
Location: Archie K. Davis Conference Center, 12 Davis Drive Research Triangle Park, North Carolina 27709 USA
Time: 8:00 am to 9:30 am
Sep
04
Location: Gross 103
Time: 4:30 pm to 5:30 pm
Sep
04
Location: Gross Hall Energy Hub
Time: 5:30 pm to 7:30 pm