Data Scientist — Penn State Meteorology and Atmospheric Science

Data Scientist — Penn State Meteorology and Atmospheric Science


Interested in driving data science innovation?

In this position you’ll collaborate on data science projects with disciplined utility experts. Example projects include predicting asset failures, analyzing aerial imagery using computer vision algorithms and geospatial statistics, forecasting power outages at fine spatiotemporal resolution, and modeling and forecasting consumer adoption of energy-efficient products and services, including demand-response programs, electric vehicles, solar, and energy-storage products. 

The ideal candidate will have significant experience using R, R Shiny, R Markdown, and Python (with a preference for fluency in all) in multiple analytical applications, such as geoinformatics, nonlinear time series analysis, machine learning (such as binomial/regression models or ensemble models), deep learning (such as NN, CNN, and RNN), and probability and statistics. As with any successful analytics project, it all starts with the data, so you should have experience extracting and transforming data from relational databases (such as Oracle or SQL Server). Time-series database experience (such as OSI PI) is a plus. 

You’ll be a full-time member of E Source Data Science. Our data science positions appeal to self-starters who welcome and excel in team-based, collaborative projects from conception to end-user handoff, providing an excellent customer experience throughout. The ability to simplify complex analyses into understandable concepts that are applicable to management and operations staff is highly desired. 

The ideal candidate has a BS and MS or PhD in computer science, math, statistics, or data science. Work experience should consist of a proven track record of efficiently conducting and coordinating data analytics projects both independently and collaboratively over period of more than two years (for junior positions) or five years (for senior positions). Exceptional educational or industry experience can offset any particular requirement. Backgrounds in diverse fields that complement data science (such as applied discipline expertise and statistics) is considered an asset. A broad background in the utility, power, or energy sector is a plus. 

Key experience

  • An MS or PhD in a numerical analysis-related field of study
  • Proficiency in scientific programming in R or Python
  • Proficiency and demonstrated experience in all phases of the data science life cycle: data compilation, data exploration, feature engineering, modeling, and communication
  • Experience developing reusable R or Python packages
  • Experience organizing interactive explorations of data into code chunks within R Notebook or Jupyter Notebook
  • Experience communicating complex technical concepts to a business audience
  • A creative mind, keen ability, and the initiative to think beyond



Source link

Similar Articles

Comments

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Advertismentspot_img

Instagram

Most Popular