Staff Data Engineer, Applied Data Science III

Electric Power Engineers • Austin, TX

5d • Remote

About The Position

EPE is seeking a Staff Data Engineer to support analytical and applied data science, data engineering, and data architecture consulting projects for utility and energy-sector clients. The role helps clients translate utility data and business requirements into well-designed data pipelines, reliable models, and integrated analytics and data science workflows. Work spans data discovery, architecture and integration design, hands-on development, machine learning, and model maintenance.

This is a hands-on individual-contributor role for a professional with 4–5 years of relevant experience, including utility-sector experience. The position delivers defined technical components and workstreams in collaboration with senior technical staff and client architects on broader architectural decisions. Depending on the engagement, work may involve direct implementation or design specifications and advisory support for client-owned implementation.

The position is remote within the U.S. Occasional travel may be needed, at 10% or less. EPE describes itself as a consulting and energy-intelligence software company serving power and energy clients, with a focus on building a modern, secure, and resilient grid.

Requirements

• Bachelor’s degree in computer science, data science, statistics, mathematics, engineering, or a closely related quantitative discipline.
• 4–5 years of relevant professional experience, including within the utility sector, with hands-on data engineering and applied data science work and demonstrated contributions to data architecture or integration design.
• Experience building and maintaining repeatable data pipelines or integrations beyond one-time data preparation and exploratory notebooks.
• Experience designing data models, schemas, relationships, and source-to-target mappings, and explaining the rationale behind design decisions.
• Strong Python and SQL proficiency, including maintainable programming, complex queries, data transformation, and troubleshooting.
• Experience with pipeline testing, scheduling or orchestration, logging, data-quality validation, and failure investigation.
• Working experience with at least one cloud or distributed-data platform, such as Databricks, Azure, AWS, Google Cloud, or an equivalent environment.
• Strong understanding of probability, sampling, statistical inference, regression, confidence and prediction intervals, and uncertainty.
• Practical experience developing and evaluating statistical or machine learning models, including appropriate validation and interpretation of results.
• Experience with Git, code review, testing, technical documentation, and reproducible analyses.
• Ability to communicate technical designs, analytical findings, assumptions, and limitations to technical and nontechnical audiences.

Nice To Haves

• Experience with Databricks, Spark/PySpark, or comparable distributed-data technologies.
• Experience with dimensional modeling, warehouse/lakehouse design, metadata management, or data catalogs.
• Experience with workflow orchestration, CI/CD, model versioning, experiment tracking, or model monitoring.
• Experience with time-series or probabilistic forecasting, Bayesian methods, simulation, or optimization.
• Familiarity with XGBoost, LightGBM, PyMC, PyTorch, or TensorFlow; expertise in every framework is not expected.
• Experience with utility datasets, DER registries, load forecasting, sensor analytics, or engineering automation.
• Master’s degree in a relevant quantitative or technical discipline.

Responsibilities

• Explore, evaluate, and understand utility datasets, including AMI interval energy, SCADA, GIS, utility asset, customer programs, and billing data.
• Design, develop, test, and maintain repeatable ETL/ELT pipelines that ingest, transform, reconcile, and deliver data from databases, files, APIs, and other approved sources.
• Develop reusable Python and SQL components for data cleansing, standardization, aggregation, validation, and feature preparation.
• Profile source data and establish automated checks for completeness, validity, consistency, uniqueness, and freshness.
• Develop record-matching and entity-resolution logic to reconcile customer, asset, device, program, and operational records.
• Investigate pipeline failures, data discrepancies, and performance issues, and document corrective actions.
• Translate business, analytical, and operational requirements into documented data architecture and integration designs for defined solutions or components.
• Develop conceptual, logical, and physical data models, entity relationship diagrams, schemas, data dictionaries, and source-to-target mappings.
• Design data flows connecting source systems, staging and storage layers, analytical datasets, models, and downstream applications.
• Evaluate and document design tradeoffs involving databases, warehouses or lakehouses, batch or API integration, performance, scalability, maintainability, and cost.
• Incorporate client requirements for data ownership, access controls, sensitive information, retention, lineage, and auditability into solution designs.
• Develop and validate forecasting models, classification schemas, anomaly-detection analyses, clustering approaches, and prioritization models appropriate to utility applications.
• Address overfitting, class imbalance, sampling bias, and time-dependent validation requirements.
• Monitor model performance and support documented recalibration, retraining, and model updates.
• Connect analytical models to reliable data pipelines and reproducible datasets, working with client deployment teams where appropriate.
• Communicate assumptions, uncertainty, limitations, and the distinction between observed, inferred, and predicted results.
• Participate in requirements workshops, technical interviews, architecture reviews, and client working sessions.
• Prepare technical reports, process maps, design documentation, and analytical presentations.
• Deliver assigned work within agreed scope, schedule, budget, and quality expectations.
• Identify and escalate data-access constraints, technical dependencies, methodological limitations, and delivery risks.
• Contribute to peer reviews, reusable technical methods, and guidance for less-experienced colleagues.
• Use AI-assisted development responsibly, validating outputs and protecting client information.

Benefits

• Comprehensive medical, dental, and vision benefits with 100% premium coverage for the employee.
• Generous PTO and paid holidays.
• MyShare Employee Ownership Program.
• Opportunity to work with industry leaders.
• 401(k) with up to a 4% match, 100% vested from day one.

What This Job Offers

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