Data Scientist

Job type:


Job Description

Company Profile:

Direct Energy generates electricity and produces natural gas, as well as selling commodities and servicing the energy needs of homes and businesses in 46 U.S. states plus the District of Columbia and 10 Canadian provinces. We also help our customers save on their energy bills through energy efficiency. Located in over 50 locations, our team of 6,000+ employees serve over 6 million residential and commercial customer relationships.

Direct Energy is a subsidiary of Centrica plc (LSE:CNA), one of the world's leading integrated energy companies with over 20 million customers and 34,000 employees worldwide. We are committed to being the most recommended energy and services provider and leading the transition to a low carbon society.

The Data Scientist will work to develop statistical models for prediction, classification, and clustering within Direct Energy. She/He will also develop IT requirements and guide projects to make data available for analytics efforts. She/He will also be responsible for developing, extracting, and maintaining logical and physical data models for data analytics. She/He will also assist the overall governance of the platform – including data integrity, access and roadmap.

Specifically, a Data Scientist will have a detailed understanding of predictive and clustering algorithms and have expertise in executing the algorithms within a Big Data environment.

This role can be based in our Iselin, NJ, Houston, TX or Pittsburgh, PA office.


  • University Degree in Mathematics, IT, Engineering, Business, Econometrics, Operations Research, or other Science 
  • 4-6 years of professional experience or academic equivalent 
  • Experience in energy industry is desired but not essential 
  • Experience in agile software development is desired 
  • Proven ability to complete projects and achieve results in an ambiguous work environment 
  • Experience using visualization techniques for presenting data and analysis 
  • Proven track record of delivering high quality analytics insights and solutions 
  • Experience communicating with diverse teams including data scientists, engineers, and business stakeholders is desired 
  • Statistical or data modeling or machine learning certification desired but not required 
  • Travel 10% 
  • Use of video/telephone conferencing and remote working technology expected
  • 2+ years of experience preparing reports and analytics for different areas including Sales, marketing, Operations and Finance 
  • Excellent knowledge of data models and management of data 
  • Experience in Business Analytics, statistical and quantitative analysis, predictive modeling 
  • Knowledge of Big Data/Hadoop tools such as HiveQL, MapReduce, and Spark 
  • Knowledge of statistical modeling in R or Python (Python is preferred) 
  • Knowledge of Spark and MLlib preferred 
  • Knowledge of machine learning algorithms such as Random Forests, Gradient Boosting, and clustering algorithms such as K-means, and neural networks 
  • Demonstrated ability to conduct data mining, design of experiments, and develop predictive models and machine learning algorithms 
  • Knowledge of power and energy systems, such as wholesale power markets (PJM, ISO-NE, MISO, CAISO, ERCOT, etc.) is preferredAbility and desire to learn new technologies 
  • Ability to communicate and establish good relations with multi-disciplinary teams 
  • Resourcefulness and ability to work with limited supervision 
  • Flexibility and ability to manage multiple tasks and deadlines 
  • Customer focus and results oriented, meeting deadlines


  • Translate complex business issues into achievable analytical learning objectives and actionable analytic projects 
  • Analyze data to identify opportunities to improve the customer experience and drive actionable insights 
  • Create predictive and clustering models utilizing SQL Server and HDFS data sources 
  • Define when predictive or clustering models could be utilized and the type of data required to make them insightful 
  • Develop, extract and maintain logical and physical data models for data analytics within Direct Energy 
  • Check and maintain data quality / hygiene of the across different systems 
  • Design customer-focused data and analytics processes and solutions for business customers 
  • In close liaison with Business Analyst, IS developers, and Information Technology team, research and define the sources to pull data and design front end solutions. 
  • Provide maintenance to existing solutions, including modifications and bug fixing activities. 
  • Respond to continuous changes in the organization to keep accurate and on-time information always available to end users. 
  • Processing, cleansing, and verifying the integrity of data used for analytics 
  • Enhancing data collection procedures to include information that is relevant for building analytic systems 
  • Extending company’s data with third party sources of information when needed 
  • Data mining using state-of-the art methods and produce actionable insight 
  • Selecting features, building and optimizing classifiers using machine learning techniques 
  • Design and develop predictive models and machine learning algorithms using advanced methodologies 
  • Provide detailed analytics reports, presentations, and documentation

The IndividualDirect Energy and its subsidiaries are an Equal Opportunity Employer - EOE AA M/F/Vet/Disability
Additional Website Text