Data Scientist - Innovation & Digital Factory

FirstEnergy at a Glance FirstEnergy (NYSE: FE) is dedicated to safety, reliability and operational excellence. Headquartered in Akron, Ohio, FirstEnergy includes one of the nation's largest investor-owned electric systems, more than 24,000 miles of transmission lines that connect the Midwest and Mid-Atlantic regions, and a generating fleet with a total capacity of more than 3,600 megawatts. About the Opportunity As a Data Scientist at FirstEnergy you will work with other data scientists and data engineers using machine learning, artificial intelligence, and statistical methods to answer critical questions and produce actionable insights for business units. A successful candidate will work on agile scrum squads and should be excited by digital enablement, innovation and new ideas, and have a passion for learning. The challenges FirstEnergy faces and the data that will help build solutions are physical, tangible, realities; voltages going across transformers, the soil our poles sit in, the proximity of our wires to trees. Applicants should be ready to challenge themselves to solve problems from data of varying type, quality, and source, so that our solutions have a meaningful impact on our customers and employees. Our digital projects benefit the community by aiding in providing safe, reliable electricity to everyone: Customer: create analytics to improve customer satisfaction along the customer journey for a lifetime as they move-in to a residence, pay their bill and move to new residences. Transmission & Distribution: develop algorithms to detect asset failures, reduce outages and provide reliable electricity to customers. Smart Meter: provide customers with the electric usage they need to make smart decisions about their home as well as reduce threats and theft in the electric system. Vegetation: Analyze geospatial data and imagery to predict, forecast, and aggregate information to support the efforts of forestry specialists to improve grid reliability. Responsibilities include: Develop Data Science products in an agile scrum squad, collaborating with Data Engineers, other Data Scientists and business stakeholders Build and test machine learning algorithms, forecasting/predictive algorithms, and optimization models Transform and model a variety of data such as tabular, text, streaming, geospatial and large volume Perform hands-on text, quantitative, statistical, financial, and operational analysis Deepen understanding of utilities structure and operations to answer the right question more effectively Identify new data sources and evaluate emerging technologies for data discovery and model development Collaborate with technical staff and peers to implement and deploy scalable data solutions Provide thought leadership by researching best practices, conducting experiments, and collaborating with industry leaders Qualifications Bachelor’s degree in quantitative discipline such as Computer Science, Machine Learning, Applied Statistics, Mathematics; Masters, PhD are beneficial Experience with machine learning models such as decision trees, random forests, and neural networks and evaluation metrics like F1 score and ROC AUC Experience in Python programming language, familiarity with Apache Spark beneficial Experience with linear regression modelling and other statistical techniques such as t-tests, confidence intervals Experience in Agile/Scrum development with DevOps methodologies geared toward rapid prototyping and piloting of cloud solutions Good presentation and communication skills, with the ability to explain complex analytical concepts to people from other fields Ability to guide other colleagues and lead research efforts in a cross-functional team Experience in building positive relationships and working with peers cross-functionally, demonstrating teamwork and collaboration Willingness to travel throughout organization and service territory and work extended hours, as required Benefits, Compensation & Workforce Diversity