Data Scientist 3 – Nuclear Operations

Company: BLOC Resources

Client: Southern Company / Southern Nuclear

Location: 260 Southfield Parkway, Forest Park, GA 30297

Pay Rate: $50.00–$56.00 per hour, based on experience and qualifications

Position Type: Contract / Supplemental Workforce

Industry: Nuclear Energy / Data Science / Advanced Analytics / Artificial Intelligence

Position Overview

BLOC Resources is seeking an experienced Data Scientist 3 – Nuclear Operations to support Southern Company and Southern Nuclear's Nuclear Technology Solutions organization.

This senior-level position is responsible for developing, validating, deploying, and maintaining advanced analytical and machine learning solutions that support nuclear operational performance, equipment reliability, predictive maintenance, and economic outcomes.

The Data Scientist will transform complex plant telemetry and operational data into actionable insights delivered through a secure, governed, cloud-native analytics environment. A major focus of this position is the production-grade implementation of analytics solutions within the Southern Nuclear Azure Databricks Lakehouse.

Because this work supports a highly regulated nuclear environment, the successful candidate must demonstrate exceptional attention to accuracy, model validation, documentation, data governance, security, traceability, auditability, and formal change management.

The ideal candidate will have approximately 10–15 years of data science and advanced analytics experience, with significant experience developing and deploying production machine learning solutions using Python, SQL, Spark, cloud technologies, and large-scale datasets.

Key Responsibilities

Advanced Analytics & Machine Learning

• Develop, test, validate, deploy, and maintain advanced statistical and machine learning models.
• Develop analytical solutions supporting nuclear operational performance, equipment reliability, predictive maintenance, anomaly detection, and related operational use cases.
• Analyze large, complex datasets to identify patterns, trends, relationships, risks, and actionable insights.
• Apply advanced statistical and machine learning techniques to solve complex operational and business problems.
• Develop predictive models using appropriate machine learning techniques, including ensemble methods, neural networks, deep learning, and other advanced approaches where appropriate.
• Develop and optimize algorithms to address complex analytical challenges.
• Lead feature engineering activities to identify and develop meaningful variables that improve model performance.
• Formulate and test hypotheses using rigorous statistical methods.
• Design analytical experiments and, where appropriate, evaluate results using structured experimentation or A/B testing methodologies.
• Ensure analytical approaches are appropriate for the intended operational application.

Model Validation & Reliability

• Apply rigorous validation techniques to ensure analytical models are accurate, reliable, explainable, and suitable for operational decision support.
• Document model assumptions, limitations, intended uses, validation results, and operational considerations.
• Evaluate model performance against established requirements and success criteria.
• Monitor deployed models over time for changes in performance.
• Identify model drift, data-quality issues, and changes in underlying operational conditions.
• Support controlled model updates as data and operating conditions evolve.
• Ensure model outputs can be traced to approved source data.
• Promote reproducibility and repeatability throughout the analytical lifecycle.

Azure Databricks Lakehouse & Cloud Analytics

• Design and implement end-to-end analytics workflows within the Southern Nuclear Azure Databricks Lakehouse environment.
• Build, maintain, and optimize analytical data pipelines.
• Develop feature datasets supporting machine learning and advanced analytics.
• Work within enterprise medallion architecture standards and established data-management practices.
• Leverage Apache Spark and distributed computing technologies to process large and complex operational datasets.
• Integrate data from approved enterprise data sources, data lakes, warehouses, and operational systems.
• Develop scalable analytical solutions capable of supporting production workloads.
• Collaborate with data engineering and platform teams on data availability, architecture, integration, and performance.
• Apply approved experiment tracking and model-lifecycle practices to support governance and repeatability.

MLOps & Production Model Deployment

• Support the development and implementation of repeatable machine learning training and deployment workflows.
• Deploy analytical and machine learning models into controlled production environments.
• Participate in the development and improvement of MLOps practices.
• Establish repeatable processes for model training, testing, validation, deployment, monitoring, and controlled updates.
• Ensure production models are maintainable, traceable, and appropriately documented.
• Coordinate with platform, engineering, and IT teams to ensure successful model integration.
• Support production analytics used for operational and business decision-making.

Time-Series & Nuclear Operational Analytics

• Analyze industrial and operational time-series datasets.
• Develop models capable of identifying abnormal equipment or system behavior.
• Apply predictive analytics to support equipment reliability and predictive maintenance.
• Evaluate historical and real-time operational data to identify meaningful performance patterns.
• Work with nuclear engineers and operational subject-matter experts to understand plant telemetry and operational context.
• Translate engineering and operational questions into measurable analytical problems.
• Ensure statistical conclusions appropriately reflect the characteristics and limitations of the underlying data.

Applied AI & Advanced Analytics

• Support approved AI-enabled analytical and search capabilities.
• Evaluate retrieval-based and other advanced AI techniques when appropriate for approved use cases.
• Ensure AI-assisted solutions are transparent, verifiable, traceable, and aligned with enterprise and regulatory expectations.
• Evaluate emerging data science and AI technologies for potential business and operational applications.
• Promote responsible and controlled implementation of advanced AI capabilities.
• Ensure AI-enabled solutions operate within established security, data-governance, and change-management requirements.

Data Governance, Security & Compliance

• Design analytical solutions in accordance with enterprise data-governance standards.
• Maintain appropriate data access controls and security requirements.
• Ensure analytical outputs are traceable to approved data sources and inputs.
• Follow established data-handling and information-security standards.
• Operate within platform security controls designed to limit unauthorized data ingress, egress, and access.
• Support auditability of data science models, analytical processes, and outputs.
• Apply appropriate data privacy, ethical data-use, and compliance practices.
• Ensure analytical solutions meet Southern Company requirements for quality, accuracy, documentation, and auditability.
• Work in accordance with nuclear safety culture and formal change-management practices.

Data Visualization & Communication

• Develop clear and effective visualizations that communicate complex analytical findings.
• Present analytical insights to technical and non-technical stakeholders.
• Use tools such as Power BI, Tableau, Python visualization libraries, or other approved enterprise tools as appropriate.
• Translate highly technical statistical and machine learning results into understandable business and operational information.
• Clearly communicate model assumptions, methodologies, limitations, risks, and conclusions.
• Develop presentations and supporting documentation for engineering, technology, analytics, and leadership stakeholders.

Cross-Functional Collaboration

• Partner closely with nuclear engineers, IT leaders, data engineers, platform teams, business analysts, domain experts, and analytics professionals.
• Participate in technical design, architecture, and solution-development discussions.
• Translate operational and engineering requirements into appropriate analytical approaches.
• Collaborate with IT and data engineering teams to integrate approved data sources.
• Coordinate with stakeholders throughout model development, validation, deployment, and operational support.
• Build effective relationships across technical and operational organizations.
• Serve as a senior data science resource on complex analytical initiatives.

Technical Leadership & Mentorship

As a senior-level Data Scientist, the successful candidate may also:

• Provide technical guidance and mentorship to junior data scientists and analytics professionals.
• Review analytical methodologies, model designs, and technical solutions.
• Promote data science standards and best practices.
• Help improve organizational capabilities in machine learning, advanced analytics, MLOps, and AI.
• Contribute to longer-term analytics and data science strategy.
• Evaluate new technologies, techniques, frameworks, and tools.
• Encourage innovation while maintaining appropriate governance and operational controls.

Required Qualifications

• Approximately 10–15 years of professional data science, advanced analytics, machine learning, or closely related experience.
• Demonstrated history of developing and implementing production-grade data science solutions.
• Advanced proficiency in Python for data analysis, statistical modeling, and machine learning.
• Strong proficiency in SQL.
• Experience working with large-scale structured datasets.
• Strong understanding of statistical modeling and statistical validation.
• Strong experience with time-series analysis.
• Experience developing and deploying machine learning models in production cloud environments.
• Experience with big-data processing and distributed computing technologies.
• Experience with Apache Spark or similar large-scale processing frameworks.
• Strong understanding of machine learning algorithms and their practical applications.
• Experience integrating data from multiple enterprise sources.
• Strong analytical and critical-thinking capabilities.
• Excellent technical documentation skills.
• Ability to clearly explain analytical methodologies, assumptions, limitations, and results.
• Strong written and verbal communication skills.
• Ability to collaborate effectively with technical, operational, and business stakeholders.

Education

Master's degree preferred in one of the following or another related quantitative discipline:

• Data Science
• Computer Science
• Statistics
• Mathematics
• Engineering
• Physics
• Applied Mathematics
• Artificial Intelligence/Machine Learning

A Ph.D. in a relevant quantitative discipline may also be highly desirable depending on the candidate's professional experience.

Technical Skills

Strong candidates should demonstrate experience with several of the following:

• Python
• SQL
• Azure Databricks
• Apache Spark
• Cloud-based analytics
• Machine learning
• Statistical modeling
• Time-series analysis
• Predictive modeling
• Predictive maintenance
• Anomaly detection
• Feature engineering
• Deep learning
• Neural networks
• Ensemble methods
• Model validation
• Model monitoring
• MLOps
• Experiment tracking
• Data pipelines
• Data lakes
• Data warehouses
• Medallion architecture
• Data integration
• Data visualization
• Power BI
• Tableau
• Python visualization libraries
• Applied AI
• Retrieval-based AI techniques
• Enterprise data governance
• Access control
• Model lifecycle management

Preferred Qualifications

• Experience supporting nuclear energy, utilities, power generation, energy, industrial operations, or another highly regulated industry.
• Experience with nuclear or industrial plant telemetry.
• Experience analyzing industrial or operational time-series data.
• Azure Databricks Lakehouse experience.
• Experience implementing scalable Spark-based analytics.
• Experience with enterprise medallion architecture.
• Experience developing predictive-maintenance or equipment-reliability models.
• Experience with anomaly-detection applications.
• MLOps experience, including repeatable model training and deployment workflows.
• Experience with enterprise data-governance frameworks.
• Understanding of role-based access controls and secure data environments.
• Experience working under formal change-management processes.
• Experience developing analytical solutions subject to audit or regulatory review.
• Experience implementing governed AI or advanced analytics capabilities.

Documentation & Quality Standards

Documentation is a critical component of this position. The Data Scientist will be expected to produce comprehensive technical documentation covering:

• Analytical objectives and intended use
• Source data and approved inputs
• Data preparation and transformation
• Feature engineering
• Model methodology
• Assumptions
• Statistical validation
• Model-performance results
• Limitations and risks
• Deployment methodology
• Operational considerations
• Monitoring requirements
• Model changes and updates

All work must support appropriate quality, accuracy, repeatability, traceability, maintainability, and auditability.

Knowledge & Competencies

The successful candidate should demonstrate:

• Exceptional analytical rigor and attention to detail.
• Advanced problem-solving and critical-thinking abilities.
• Ability to work with complex and highly technical datasets.
• Strong understanding of statistical and machine learning principles.
• Ability to balance innovation with security, governance, and operational controls.
• Strong technical leadership capabilities.
• Ability to communicate effectively with engineers, technology professionals, analysts, and senior stakeholders.
• Strong organizational and project-management skills.
• Ability to independently manage complex analytical assignments.
• Ability to work effectively in a multidisciplinary environment.
• Commitment to ethical and responsible use of data and artificial intelligence.

Behavioral Attributes

The successful candidate is expected to demonstrate Southern Company's core values and professional expectations, including:

• Safety First
• Act with Integrity
• Intentional Inclusion
• Superior Performance

Candidates should also demonstrate professionalism, accountability, collaboration, technical curiosity, attention to detail, and the ability to operate successfully in an environment with formal controls and regulatory oversight.

Nuclear & Regulatory Environment

Because this position supports Southern Nuclear operations, the selected candidate must be comfortable working in a highly regulated nuclear environment where data accuracy, cybersecurity, documentation, quality assurance, traceability, and formal change control are critical.

The position may require compliance with applicable nuclear regulatory and company requirements, including background screening, testing, training, security requirements, and other qualification processes, as required by policy.

Work Location

260 Southfield Parkway

Forest Park, GA 30297

On-site and work-location requirements will be aligned with Southern Company's business and operational needs.

Compensation

$50.00–$56.00 per hour, based on experience and qualifications.

Final compensation will consider the candidate's overall data science experience, Azure Databricks and cloud expertise, machine learning background, production deployment experience, nuclear/utility industry experience, and other relevant qualifications.

Why Join BLOC Resources?

This opportunity provides an experienced Data Scientist the ability to:

• Support advanced analytics within the nuclear power industry.
• Work with complex nuclear operational and equipment data.
• Develop production-grade machine learning solutions.
• Work within an enterprise Azure Databricks Lakehouse environment.
• Contribute to predictive maintenance, equipment reliability, anomaly detection, and operational-performance initiatives.
• Collaborate directly with nuclear engineers, technology professionals, and analytics teams.
• Gain exposure to governed AI and advanced analytics in a highly regulated environment.
• Contribute to the modernization of data-driven nuclear operations.
• Receive ongoing recruiting and workforce support from BLOC Resources.

Ideal Candidate Profile

The strongest candidate will be a senior Data Scientist with approximately 10–15 years of experience who combines advanced machine learning and statistical expertise with hands-on production implementation capabilities.

The candidate should be highly proficient in Python, SQL, Spark, cloud analytics, machine learning, time-series modeling, model validation, and production deployment.

Experience with Azure Databricks, MLOps, industrial time-series data, predictive maintenance, equipment reliability, nuclear energy, utilities, or another highly regulated environment would make a candidate particularly competitive.

Most importantly, this individual must understand that success in a nuclear environment requires more than building a high-performing model—the solution must also be explainable, controlled, documented, secure, repeatable, traceable, and auditable.

Equal Employment Opportunity

BLOC Resources is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment consistent with applicable federal, state, and local requirements.