14548 – Principal Data Scientist (onsite) – Juno Beach, FL

Start Date: ASAP
Type: Temporary Project
Estimated Duration: 12 months with possible extensions
Work Setting: 100% of the time at the Client’s site. No telecommuting or remote work. This is a non-negotiable requirement from the client
Only candidates able to relocate as required should apply to avoid removal from future consideration.

Our Client is hiring a Principal Data Scientist
19323 Required:
• Experience with Python and SQL for data engineering and ML model development [4+ years combined in data science and data engineering];
• Experience with at least one major cloud AI/ML platform (AWS, GCP, or Databricks);
• Experience with machine learning model development, training, validation, deployment, and monitoring;
• Experience with scalable data pipeline design and implementation using distributed computing frameworks;
• Experience with medallion-layer data architectures (Bronze/Silver/Gold);
• Experience with Agile/SAFe delivery practices;
• Bachelor’s Degree in Computer Science, Data Science, Engineering, or related field;

19323 Preferred:
• Experience with SAP S/4HANA or other ERP systems as a data source for analytics;
• Experience with agentic AI frameworks and LLM-based workflow automation;
• Experience with version control tools such as GitHub and enterprise data governance practices;
• Experience in the utility or energy industry;
• Experience with Agile/SAFe delivery model;
• Master’s Degree in a quantitative discipline;

19323 Responsibilities:
• Design and implement scalable data pipelines ingesting procurement, materials, and financial data from enterprise source systems into cloud analytics platforms;
• Build, train, validate, and deploy machine learning models for spend classification, commodity categorization, materials de-duplication, and market research enrichment;
• Develop and maintain medallion-layer data architectures (Bronze/Silver/Gold) to ensure data quality, lineage, and governance;
• Implement agentic AI workflows for multi-step reasoning, classification, and end-to-end procurement tracking;
• Register, version, and monitor models through a structured ML lifecycle including development, validation, deployment, and retraining;
• Build and maintain dashboards and reporting layers that surface actionable insights to business stakeholders;
• Collaborate with cross-functional SMEs to analyze complex supply chain and procurement issues and develop data-driven solutions;

Please see below some more positions you may be interested in:
19307 Required:
• Availability to work 100% of the time at the Client’s site in Juno Beach, FL (required);
• Experience with Python (pandas, numpy, scikit-learn, stats models) for data science workflows;
• Experience with time-series forecasting models and methods (ARIMA, SARIMAX, gradient boosting) and production deployment;
experience taking models from research/development through production deployment with proper versioning, monitoring, and maintenance
• Experience with API integration for weather and external data sources and data engineering pipelines;
• Experience with AWS services (EC2, S3, Lambda, SageMaker) and Infrastructure-as-Code practices;
• Experience with SQL databases and large-scale data queries and optimization;
• Experience with dashboard development using Streamlit, Plotly, or similar frameworks;
• Experience with model evaluation metrics (MAE, RMSE, MAPE) and version control (Git);


19307 Preferred:
• Experience with advanced feature engineering, uncertainty quantification, and probabilistic forecasting methods;
• Experience with energy markets and renewable generation forecasting;
• Experience with Agile project management tools (Jira, Confluence);


19307 Responsibilities:
• Lead end-to-end forecasting model development for Load, Solar, and Wind generation from conception through production deployment;
• Build automated retraining and evaluation frameworks with monitoring dashboards;
• Develop data connectors for weather APIs and data warehouse systems;
• Design and maintain scalable pipelines for real-time and batch forecasting operations;
• Create interactive dashboards and present forecasting insights to business stakeholders including trading, operations, and engineering teams;
• Implement robust error handling, alerting mechanisms, and recovery procedures for production forecasting systems;
• Optimize model performance and ensure forecasting accuracy meets operational deadlines and standards;

Why apply?
• Gain experience with one of the world's largest solar and wind energy providers, which last year briefly became the most valued U.S. energy company;
• Work with a great team of professionals and learn newest technologies and approaches;
• Enjoy our Client’s wonderful campus with top-notch facilities for work and recreation;
• Benefit from multiple projects extensions;
• Receive support and advice from Vitaver consultants who are already working at our Client’s site;
• Get extra cash by participating in Vitaver Successful Completion Bonus Program;
• Always get paid in full and on time.