Sr Data Scientist

Sr Data Scientist

Apply the appropriate data science or analytical methods to extract knowledge and insights from data, which may take the form of time-series (power plant equipment data, environmental data or other), structured (relational data stores), and unstructured (text and multi-media) data sets. Closely collaborate with various internal stakeholders, information architects, data engineers, project/program managers, and other teams to turn data into critical information to inform decision making. This requires understanding business needs, providing and receiving regular feedback, and planning the proper transfer of developed solutions. Mine big and small data for insights, using advanced statistic and machine learning methods. Validate findings with the business by sharing analysis outputs in a way that can be understood by business stakeholders. Fill role of a subject matter expert in the areas of artificial intelligence, machine learning, feature engineering, data mining, and data manipulation/storage. Demonstrate commitment to continuous learning and professional development in technical subject matter. Share knowledge with team members, and business stakeholders, and IT partners. Collect, cleanse, standardize and analyze data from a variety of internal and external sources. Produce novel insights to help inform business actions using statistical modeling and machine learning techniques on complex data-sets on the order of several terabytes or petabytes.

PRIMARY DUTIES AND ACCOUNTABILITIES

• Develop key predictive models that lead to delivering reduced overall annual expense for nuclear, performance improvement, and optimize specific performance criteria. Develop and recommend data sampling techniques, data collections, and data cleaning specifications and approaches. Apply missing data treatments as needed.
• Analyze data using advanced analytics techniques in support of process improvement efforts using modern analytics frameworks, including but not limited to Python, R, Scala, or equivalent; Spark, Hadoop file system and others
• Access and analyze data sourced from various Company systems of record. Support the development of strategic business and program implementation plans.
• Access and enrich data warehouses across multiple Company departments. Build, modify, monitor and maintain high-performance computing systems.
• Provide expert data and analytics support to multiple business units
• Works with stakeholders and subject matter experts to understand business needs, goals and objectives. Work closely with business, engineering, and technology teams to develop solution to data-intensive business problems and translates them into data science projects. Collaborate with other analytic teams across Exelon on big data analytics techniques and tools to improve analytical capabilities.

MINIMUM QUALIFICATIONS

• Education: Bachelor's degree in a Quantitative discipline. Ex: Data Science, Data Analytics, Applied Mathematics, Statistics, Computer Science, Operations Research, or related field
• Experience: Between 5-8 years of relevant experience developing hypotheses, applying machine learning algorithms, validating results to analyze large datasets and extract actionable insights is required. Previous research or professional experience applying advanced analytic techniques to large, complex datasets.
• Analytical Abilities: Strong knowledge in at least two of the following areas: machine learning, artificial intelligence, statistical modeling, data mining, information retrieval, or data visualization.
• Technical Knowledge: Proven experience in developing and deploying predictive analytics projects using one or more leading languages (Python, R, Scala, etc.).
• Communication Skills: Ability to translate data analysis and findings into coherent conclusions and actionable recommendations to business partners, practice leaders, and executives. Strong oral and written communication skills.

PREFERRED QUALIFICATIONS

• Education: Masters, or PhD in a Quantitative discipline.
• Experience: Strong Python proficiency with scikit-learn, pandas, numpy; 3+ years experience building and shipping real-world business applications of classification/regression models in production; Expertise in feature engineering and model evaluation and tuning; Experience with MLOps tools (MLFlow or Azure ML) for model tracking and deployment; Ability to communicate technical concepts clearly to non-technical stakeholders; Familiarity with time series or volatility analysis, clustering, decision tree learning, artificial neural networks etc.; Experience with imbalanced classification problems; Nice to have - Domain knowledge in energy, finance, or commodity pricing