Southern Company is an energy provider whose role supports enterprise pricing, forecasting, valuation, data platforms, and AI initiatives. The Data Scientist develops and applies analytics, machine learning, AI, and data engineering practices to build models, pipelines, curated data assets, and production-ready analytical solutions across multiple seniority levels.
Analyze and organize customer/market data for pricing, planning, and forecasting
Support the development and validation of reusable data pipelines and curated datasets under guidance
Maintain and validate existing models and recurring reports; troubleshoot data issues
Develop baseline statistical or ML models under guidance (e.g., regression, classification, forecasting)
Use approved AI tools to automate routine analysis and reporting (e.g., templated notebooks, prompt-driven summaries)
Document assumptions, code, and data lineage; support audit and review requests
Continuously identify small improvements to data quality, model performance, and efficiency
Assist with monitoring data pipeline results, investigating data quality issues, and documenting corrective actions
Design and develop statistical and ML models for business problems (forecasting, valuation, segmentation, anomaly detection)
Build and maintain scalable analytical and data engineering pipelines, reusable curated datasets, and feature assets; implement validation and data quality checks
Develop and optimize data ingestion, transformation, and orchestration processes within Databricks and Azure environments
Create AI-enabled analytical tools (e.g., guided Q&A over curated data, automated insight generation) with measurable value
Develop dashboards and stakeholder-ready outputs; explain model results and tradeoffs
Collaborate cross-functionally to define requirements, success metrics, and adoption approach
Own delivery for assigned workstreams
Lead end-to-end delivery of advanced analytics and AI solutions (design, build, deploy and monitor)
Design, develop, and maintain scalable cloud-based data pipelines and curated datasets that support analytics, reporting, AI, and business operations
Define modeling standards, validation approaches, and monitoring thresholds; ensure explainability and audit readiness
Drive adoption by integrating models and AI tools into business workflows and decision processes
Partner with leadership to prioritize use cases, manage tradeoffs, and quantify business impact
Continuously improve data quality and governance practices to support scalable AI across markets
Partner with IT and enterprise data teams to improve platform reliability, performance, security, and data governance
Accountable for domain AI outcomes and risk posture, including final technical approval for production readiness
Prioritize AI use cases based on business value, feasibility, and risk
Define and enforce SouthStar standards for model development, validation, monitoring, documentation, and responsible AI use, aligned with enterprise frameworks
Establish reusable AI/ML frameworks, templates, and best practices to accelerate delivery across teams
Lead cross-functional delivery of production AI solutions (automation, forecasting, decision support, AI assistants)
Drive workforce enablement (training, playbooks, coaching) to elevate AI adoption and productivity
Provide technical direction across multiple teams and functions, leading through influence rather than formal authority
Mentor junior staff on modeling practices and documentation; conduct technical reviews and guide complex problem-solving
Stay current on GenAI, NLP, and advanced ML trends and assess their applicability to SouthStar’s business
Provide strategic direction for SouthStar’s cloud data platform architecture, ensuring alignment across data engineering, analytics, and AI capabilities
Establish data engineering design standards, reusable patterns, and operating practices for secure, reliable, and scalable data products
Qualification
Required
Required: Bachelor's degree in a quantitative field (e.g., mathematics, statistics, economics, data science, computer science, or similar)
0-2 years of experience (including internships/co-ops) in analytics, data, or modeling
Working knowledge of SQL and relational databases (e.g., SQL Server, Oracle, MySQL)
Hands-on programming for analysis (Python or R) and basic ML/statistical modeling
Ability to follow established standards for documentation, validation, and reproducibility
Able to communicate results clearly to technical and non-technical stakeholders
Basic understanding of data engineering concepts, including data pipelines, data quality validation, and cloud-based analytics platforms
Ability to develop or support reusable data transformations and follow established data engineering standards
Required: Bachelor's degree in a quantitative field (e.g., mathematics, statistics, economics, data science, computer science, or similar)
3-5 years' experience in analytics/modeling and data processing
Demonstrated ability to build and manage models in a business environment
Experience working with large data using SQL and modern analytics platforms (e.g., Databricks/Spark/Azure/AWS)
Experience developing and maintaining production data pipelines using Databricks, Spark, Azure Data Factory, or comparable cloud technologies
Strong programming skills in Python or R; solid SQL proficiency
Experience with feature engineering, model evaluation, and performance tuning
Experience with dashboards/visualizations (e.g., Power BI, Tableau, SSRS) to communicate insights
Strong understanding of data governance basics (access, quality checks, and documentation)
Understanding of modern data engineering practices, including data ingestion, transformation, orchestration, data quality monitoring, and pipeline automation
Experience building reusable, curated datasets and supporting production analytics environments
Required: Master's degree in analytics, statistics, data science, computer science, or a related quantitative field
5-10 years of experience in analytics/data science, modeling, and large-scale data work
Hands-on experience delivering machine learning/AI solutions and/or production-level model deployment
Experience manipulating large databases using SQL and platforms such as Databricks/Spark/Azure/AWS
Experience designing and implementing scalable data pipelines and cloud-based data solutions in Databricks and Azure environments
Advanced modeling breadth (supervised/unsupervised methods) and strong statistical foundations
Ability to design validation, monitoring, and retraining plans (drift detection, performance thresholds)
Strong troubleshooting and documentation skills for complex analytical systems
Technical leadership and stakeholder management; able to drive alignment across teams
Strong understanding of data engineering concepts, including ETL/ELT, data modeling, pipeline orchestration, and data quality management
Hands-on experience with Delta Lake, Spark optimization, Azure Data Factory, and cloud-native data platforms
Required: Master's degree in analytics, statistics, data science, computer science, or a related quantitative field
10+ years of experience in analytics/data science, including a strong track record delivering enterprise-scale data and AI solutions
Extensive experience manipulating large data using SQL and platforms such as Databricks/Spark/Azure/AWS
Demonstrated success defining and scaling AI capabilities, frameworks, or platforms with strong execution
Demonstrated experience leading enterprise data platform and data engineering initiatives in Databricks and Azure environments
Expert-level modeling breadth (e.g., NLP, deep learning, Bayesian methods, clustering, neural networks) and strong statistical foundations
Proven ability to define reusable AI/ML frameworks, standards, and governance guardrails
Experienced in complex integrations/migrations across data sources and platforms such as Databricks, Azure; sets architectural direction in partnership with IT
Demonstrated leadership in analytical model design/ development/ testing/ troubleshooting/ documentation for complex analytical systems
Strong stakeholder management capabilities and a proven ability to align teams
Expert understanding of modern data architecture, data modeling, ETL/ELT design, pipeline orchestration, and cloud-based data engineering practices
Deep experience with Databricks, Azure Data Factory, Delta Lake, Spark, and related cloud technologies
Ability to establish data engineering standards, data quality frameworks, observability, and operational practices for scalable analytics and AI solutions
Preferred
Preferred: Master's degree (or in progress) in a quantitative discipline
Preferred: Exposure to energy/utility markets or pricing/forecasting concepts (through coursework or experience)
Preferred: Exposure to Databricks, Spark, Azure, or similar modern data and analytics technologies through coursework, internships, or work experience
Preferred: Master's degree in analytics, statistics, data science, computer science, or similar
Preferred: PhD (or in progress) in one of the above disciplines
Preferred: PhD in one of the above disciplines; Project Management Professional (PMP) or equivalent leadership certification
Benefits
Annual incentive awards for eligible employees
Health benefits designed to support physical well-being
Welfare benefits designed to support physical, financial, and emotional/social well-being
Retirement benefits designed to support financial well-being
Additional compensation, such as an incentive program, subject to the terms and conditions of the applicable incentive plan(s)
Hybrid work schedule of four days in-office and one day remote per week, subject to change per business needs
Southern Company headquartered in Birmingham, Alabama, is the shared services division of Southern Company.
