Data Scientist - 21005

Employment Type	Full-Time
Priority Location	Remote (Latin America, India, Pakistan)
Working Hours	Monday – Friday, 8:00 AM – 5:00 PM EST
Target Start Date	ASAP (Urgent Hiring)
Compensation	Final offer based on experience, skills, and interview performance

Our client is a renewable energy developer, owner, and operator of distributed solar and energy storage assets across the United States. The organization focuses on sustainable land use and environmental restoration while deploying clean power infrastructure to revitalize local communities.

This position sits within the Asset Management team, which oversees a growing portfolio of distributed generation projects across the United States. Reporting to the VP of Asset Management, the Data Scientist will support and co-lead the development of data infrastructure (including data warehousing) necessary to ingest telemetry and operational data from solar photovoltaic (PV) and Battery Energy Storage System (BESS) sites.
You will integrate site-level operational datasets with enterprise platforms—including accounting, CRM/ERP, CMMS, and satellite weather data providers—to drive meaningful analytics, streamline reporting pipelines, and implement AI-driven predictive solutions.

• Build, optimize, and maintain ETL/ELT data pipelines using SQL and cloud-native architectures to ingest, structure, and store time-series telemetry data.
• Leverage APIs to extract data from Data Acquisition Systems (DAS), equipment manufacturers (inverters, transformers, weather stations), the National Weather Service (NOAA), and third-party weather data providers.
• Support the setup and scalability of data warehousing infrastructure integrated across enterprise systems (accounting, CRM/ERP, CMMS).

• Extract, clean, and analyze large-scale time-series datasets related to solar and energy storage plant performance.
• Partner with performance engineers to develop predictive models forecasting plant output, troubleshooting underperforming PV and BESS assets, diagnosing component failures, and enforcing capacity guarantees.
• Apply data mining, feature engineering, and statistical/machine learning methods to drive operational and cost efficiencies.

• Develop and maintain automation scripts for internal operational monitoring and external stakeholder reporting.
• Utilize Generative AI coding assistants (e.g., Claude Code) and Large Language Models (LLMs) to accelerate code development, automate data processing workflows, and streamline analytics.
• Translate complex data insights into clear presentations and recommendations for both technical and non-technical leadership.

• Experience: Minimum 5 years of experience bridging performance engineering and data science, with at least 2 years leading cross-functional data science initiatives.
• Education: Master's degree in Computer Science, Data Science, Mathematics, Physics, Electrical Engineering, or a related field.
• Programming & Systems: Strong proficiency in Python, R, and SQL for modeling, data analysis, and automation.
• Cloud & BI Tools: Practical experience with cloud platforms (AWS or Azure), advanced Excel (VBA/macros), and business intelligence/analytical tools (e.g., Power BI, Tableau, NumPy, Hex).
• AI & Workflow Acceleration: Hands-on experience using Generative AI tools and LLMs to automate code generation and data processing.
• Time-Series Analytics: Proven track record working with real-world time-series data across the full lifecycle—from ingestion and cleaning to validation, deployment, and executive reporting.

• Background in the power industry with experience in solar performance modeling tools (e.g., pvlib, SAM, PVSyst).
• Familiarity with ASTM and IEC standards for PV plant performance testing.
• Knowledge of SCADA/DAS platforms (e.g., AlsoEnergy, Powerfactors, Ignition, PI System) and CMMS software (Fiix, Maximo, Sitetracker).
• Experience deploying machine learning models and AI-driven workflows in production environments.
• PMP or relevant project management certification.