Sr Data Scientist

PECO; Philadelphia (Philadelphia County); On-site; USD 104,000 - 156,000; Full time

Benefits offered by this job

401(k) match

Medical, dental, and vision insurance

Life and disability insurance

Generous paid time off

Employee Assistance Program

Wellbeing programs

Referral bonus

Job summary

PECO in Philadelphia seeks a data science professional to apply the scientific method to extract insights from large-scale data and support business decisions and operational improvements.

You will build predictive models and analytics capabilities across structured, unstructured, and time-series data, collaborating with internal stakeholders to translate complex problems into actionable initiatives.

Qualifications

• Bachelor's degree in a quantitative field (e.g., Applied Mathematics, CS, Finance, OR, Physics, Statistics, or related).
• 4–7 years of experience in ML, data analysis, multi-terabyte datasets, and generating insights.
• Experience applying analytic techniques to large, complex datasets.
• Strong knowledge in at least two areas: ML/AI, statistical modeling, data mining, information retrieval, or data visualization.
• Proven experience deploying predictive analytics using Python, R, Scala, etc.
• Unix-based OS experience and open-source environment familiarity.
• Strong oral and written communication skills.

Responsibilities

• Develop predictive models to improve customer experience, operations, and safety practices.
• Design data sampling techniques, data collection approaches, and cleaning specs.
• Apply missing data treatments as needed.
• Use advanced analytics and modern frameworks including Spark/Hadoop.
• Access and analyze data from multiple systems to support strategic plans.
• Enrich data warehouses and build/maintain HPC systems.
• Provide expert data and analytics support to multiple business units.
• Collaborate with stakeholders to translate data problems into projects.
• Collaborate with Exelon analytics teams to apply big data techniques.
• Mine big and small data using time-series, structured, and unstructured data.
• Validate findings with business stakeholders and present outputs clearly.
• Serve as SME in AI, ML, feature engineering, data mining, and data manipulation/storage.
• Collect, cleanse, standardize, and analyze data from internal and external sources.
• Produce novel insights using statistical modeling and ML for terabytes/petabytes datasets.
• Support business unit planning with ML technology perspectives.
• Advise stakeholders on ML findings and actions.
• Educate stakeholders through presentations, workshops, and publications.
• May work extended hours during storms or emergencies.

Skills

Machine learning

Statistical modeling

Data mining

Python

R

SQL

Communication skills

Education

Bachelor's degree in a quantitative field

Master's degree or PhD (preferred)

Tools

Spark

Hadoop

Azure

Unix

Scala

Time-series tools

Job description

This role applies the scientific method to extract insights from large-scale data to support business decisions and operational improvements. You will build predictive models and advanced analytics capabilities across structured, unstructured, and time-series datasets, working closely with internal stakeholders.

Key Responsibilities

• Develop key predictive models aimed at improving customer experience, operating performance, and safety best practices.
• Design and recommend data sampling techniques, data collection approaches, and data cleaning specifications.
• Apply missing data treatments as needed (25%).
• Use advanced analytics to support process improvement efforts using modern analytics frameworks (15%), including Python, R, Scala, or equivalent; and Spark, Hadoop file system, and related technologies.
• Access and analyze data from multiple Company systems of record to support strategic business, marketing, and program implementation plans (15%).
• Access and enrich data warehouses across multiple Company departments, and build, modify, monitor, and maintain high-performance computing systems (5%).
• Provide expert data and analytics support to multiple business units (20%).
• Partner with stakeholders and subject matter experts to understand business needs, goals, and objectives, and translate data-intensive business problems into data science projects.
• Collaborate with other analytics teams across Exelon to apply big data analytics techniques and tools that improve analytical capabilities (20%).
• Mine big and small data for insights using advanced statistical and machine learning methods, including time-series (smart-meters, smart-grid, and other IoT), structured (relational data stores), and unstructured (text and multimedia).
• Validate findings with business stakeholders and share analysis outputs in a format they can understand.
• Serve as a subject matter expert in artificial intelligence, machine learning, feature engineering, data mining, and data manipulation/storage.
• Collect, cleanse, standardize, and analyze data from internal and external sources.
• Produce novel insights using statistical modeling and machine learning for complex datasets on the order of several terabytes or petabytes.
• Support business unit strategic planning with a strategic view of machine learning technologies.
• Advise key stakeholders on machine learning findings and recommend courses of action to redirect resources and address emerging operational and business issues.
• Educate stakeholders on advanced analytics capabilities through internal presentations, training workshops, and publications.
• May be required to work extended hours for coverage during storms or other energy delivery emergencies.

Required Qualifications

• Bachelor's degree in a Quantitative discipline (examples include Applied Mathematics, Computer Science, Finance, Operations Research, Physics, Statistics, or related field).
• 4 to 7 years of relevant experience developing hypotheses, applying machine learning algorithms, validating results, analyzing multi-terabyte datasets, and extracting actionable insights.
• Previous research or professional experience applying advanced analytic techniques to large, complex datasets.
• Strong knowledge in at least two areas: machine learning, artificial intelligence, statistical modeling, data mining, information retrieval, or data visualization.
• Proven experience developing and deploying predictive analytics projects using one or more leading languages (Python, R, Scala, etc.).
• Experience working within an open source environment and Unix-based OS.
• Ability to translate data analysis and findings into coherent conclusions and actionable recommendations for business partners, practice leaders, and executives.
• Strong oral and written communication skills.

Technology Stack

• Python, R, Scala
• Spark, Hadoop file system
• Unix-based OS
• Azure
• SQL
• Data warehouses
• High-performance computing systems
• Machine learning, artificial intelligence
• Feature engineering, data mining
• Data manipulation/storage
• Statistical modeling

Compensation and Benefits

• Annual salary range: USD 104,000 to 156,000 per year (final annual salary varies based on skills, qualifications, experience, and other factors, including $104,000.00/Yr. to $143,000.00/Yr. as listed).
• Annual bonus for eligible positions: 15%.
• 401(k) match and annual company contribution.
• Medical, dental, and vision insurance.
• Life and disability insurance.
• Generous paid time off options, including vacation, sick time, floating and fixed holidays, maternity leave and bonding/primary caregiver leave, or parental leave.
• Employee Assistance Program and resources for mental and emotional support.
• Wellbeing programs including tuition reimbursement, adoption and surrogacy assistance, and fitness reimbursement.
• Referral bonus program.
• And much more.

Preferred Qualifications

• Provide senior oversight for apprentice program.
• Masters or PhD in a Quantitative discipline (examples include Data Science, Data Analytics, Applied Mathematics, Computer Science, Finance, Operations Research, Physics, Statistics, or related field).
• Experience with data structures related to smart-meters, billing, or outage management systems.
• Prior exposure to the utilities or broader energy sector.
• Prior exposure to the full data science lifecycle, including data acquisition, maintenance, processing, analysis, and communication.
• Strong understanding of relevant theories in machine learning, statistics, probability theory, data structures and algorithms, optimization, and related areas.
• Expert level coding skills (Python, SQL, etc.) and experience developing in the Azure environment.
• Proficiency in database management and working with large datasets to create, edit, update, join, append, and query data from columnar and big data platforms.
• Ability to translate executive and analytics leaders' vision and guidance into methods and analytics.
• Strong time management and presentation skills.

Additional Information

Exelon-sponsored compensation and benefit programs may vary or not apply based on length of service, job grade, job classification, or represented status. Eligibility is determined by the written plan or program documents.

Role Details

• Location: Philadelphia, PA (onsite)
• Minimum experience: 4 years