Operations Data Engineering Analyst

Southern Company • Birmingham, AL

4d • Onsite

About The Position

This position will function as part of the Southern Power Monitoring & Diagnostics (M&D) Center, which provides remote monitoring and diagnostic support to the SPC fleet of gas, solar, wind, and energy storage assets. The Operations Data Engineering Analyst supports both operational data infrastructure and AI/ML data readiness. The role assists the PI System Administrator with daily operation, maintenance, and expansion/migration of SPC’s AVEVA PI and AspenTech IP.21 historian environments, including tag management, Asset Framework (AF) configuration, analytics deployment, PI Vision development, data quality monitoring, and proactive remediation. The role also extracts, transforms, curates, and delivers clean, structured datasets from PI and IP.21 into downstream data engineering platforms such as Databricks to support M&D’s growing AI and machine learning portfolio, including iSight anomaly detection, predictive analytics models, and AI agents. In short, this role owns the data journey from raw sensor ingestion in PI through curated, AI-ready datasets — ensuring the M&D team always has trusted, high-quality, well-engineered data to power both real-time monitoring and advanced analytics. This position will closely interface with the Aveva PI/ AspenTech IP.21 System Administrator, M&D Analysts, AI/ML Analysts, Renewable Performance Engineers, Renewable, Gas, and Commercial Operations, the SPC Technology Organization, SCADA teams, and plant personnel.

Requirements

• Bachelor's degree in Engineering (Electrical, Computer, Instrumentations and Controls), Computer Science, Data Science, or a related technical field — required.
• 2-3 years of hands-on experience with AVEVA PI System, including PI Data Archive, PI Asset Framework (AF), PI Vision, and PI Interfaces/Connectors.
• Proficient in Python for data extraction, transformation, pipeline development, and automation (Pandas, NumPy, Web API calls, scripting).
• Proficient in SQL for data querying, integration, and manipulation across relational databases and data platforms.
• Familiar with Databricks, Apache Spark, or equivalent data engineering platforms — including ETL/ELT pipeline development, Delta Lake, and feature store concepts.
• Experience with data quality monitoring, validation, remediation, and surrogation in an operational/industrial context.

Nice To Haves

• Master's degree in Engineering (Electrical, Computer, Instrumentation & Controls), Computer Science, Data Science, or a related technical field - preferred.
• Working knowledge of PI DataLink, PI Web API, and PI Connect for data extraction and downstream integration.
• Experience developing and deploying AF Analytics, calculated attributes, event frames, and notifications.
• Foundational understanding of ML model deployment pipelines — including feature engineering, data labeling, model training data requirements, and inference data delivery.
• Experience with Power BI, Tableau, or similar BI tools for dashboard development and operational reporting.
• Experience in power generation, renewables, or utilities operations.
• Experience with AspenTech IP.21, dataPARC, eDNA etc.
• Familiarity with Ignition/other SCADA systems.
• OPC DA/UA, DNP3, Modbus protocols and data acquisition architectures.
• AVEVA / OSIsoft PI System accreditation.

Responsibilities

• Support the PI/IP.21 Administrator in the creation, modification, scaling, and decommissioning of PI/IP.21 tags across gas, solar, wind, and energy storage assets. Ensure tag naming conventions, point types, and compression settings are consistent with fleet-wide standards.
• Create, modify, and delete AF elements, attributes, templates, and hierarchies to reflect fleet changes (new sites, equipment swaps, decommissions). Maintain AF structure integrity across all OEMs (solar inverters, wind turbines, gas turbines, batteries, and BOP equipment).
• Develop, test, and deploy PI AF Analytics (calculated attributes, rollup expressions, event frames) in test and production environments. Validate analytic outputs against expected results prior to production deployment.
• Continuously monitor data quality across PI and IP.21 platforms — identifying stale tags, flatlined signals, bad values, communication failures, scaling errors, and missing data. Proactively remediate issues before they impact downstream analytics, dashboards, or AI models. Support data surrogation processes where needed.
• Design, develop, and maintain real-time PI Vision screens and dashboards for fleet monitoring, equipment health, data quality, and KPI tracking. Update displays as new sites are onboarded or fleet configurations change.
• Assist the PI/IP.21 Administrator with integrating new generation and storage sites into the PI/IP.21 System, including interface/connector configuration, tag provisioning, AF buildout, initial data validation, and PI Vision screen creation.
• Serve as a resource for operations, performance, and analytics teams who need to extract data from PI/IP.21. Provide support and guidance using PI DataLink, IP.21 Excel Connector, Python, SQL, PI Web API, and PI Connect to enable self-service data access and integration with downstream tools.
• Assist in diagnosing and resolving data flow issues, interface communication failures, archive gaps, and system errors within the PI and IP.21 environments. Escalate infrastructure-level issues to the PI/IP.21 Administrator or IT as appropriate.
• Build and maintain repeatable data curation pipelines that clean, validate, deduplicate, align timestamps, handle missing values, and resolve data quality issues — producing trusted, well-documented datasets for AI/ML model training and inference in Databricks.
• Partner directly with the AI/ML Analyst to understand model input requirements, feature definitions, labeling schemas, data frequency needs, and quality thresholds. Translate these requirements into actionable data engineering tasks and deliver datasets that meet model specifications.
• Validate curated datasets against AI model input specifications — checking for completeness, balance, feature drift, outliers, and schema compliance in/outside Databricks. Flag and resolve data issues before they enter training or inference pipelines.
• Monitor health and performance of data pipelines, alerting on failures, latency, or data quality degradation. Continuously improve pipeline efficiency, reliability, and scalability as the fleet and AI use cases grow.
• Build and maintain strong working relationships with the PI/IP.21 Administrator, AI/ML Analysts, M&D Analysts, Renewables Performance Engineers, Renewable, Gas, and Commercial Operations, SCADA teams, Technology Organization developers, and plant personnel.
• Maintain thorough documentation of PI configurations, AF structures, tag inventories, data pipeline architectures, dataset catalogs, and standard operating procedures.
• Incorporate industry best practices, lessons learned, and feedback into daily operations. Participate in fleet-wide standardization efforts and data governance initiatives.
• Stay current on AVEVA PI System updates, data engineering best practices (Databricks), AI/ML pipeline methodologies, and relevant industry trends.

Benefits

• competitive base salary
• annual incentive awards for eligible employees
• health, welfare and retirement benefits designed to support physical, financial, and emotional/social well-being
• additional compensation, such as an incentive program

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level