Data & Analytics Developer II - Data Scientist

CLIENT HIGHLIGHT
The client you will be working for is a Fortune 500 Energy and Industrial Technology Company. This opportunity will give you experience in the energy transition sector with a company that is a globally recognized leader in power generation, wind energy, electrification, and grid solutions — and one of the most storied industrial brands in the world.

LOCATION
Greenville, South Carolina, 29615-4614

COMPENSATION
$46.00–$53.00 per hour

SCHEDULE
Monday-Friday

Hybrid – few days in office

CONTRACT TERM
1 year with high likelihood of extension or conversion to full-time employee.

POSITION OVERVIEW – Data & Analytics Developer II - Data Scientist
You’ll use data and AI to help the team plan better and spot problems early. You’ll work between the engineers, the business team, and the IT team, figuring out what data is needed and how to use it. You’ll build models that ask, “what if our plan changes?” and track real project progress in tools like P6 to see where things are drifting off plan. Then you’ll turn the results into clear reports that leaders can use to make decisions.

RESPONSIBILITIES

• Analyze data from enterprise systems (SAP, Salesforce, Databricks, Power BI) to find patterns, gaps, and ways to improve
• Work with Program Managers and Operations leaders to decide what data is needed and how it should be used
• Clean and check large datasets (often 100k+ rows) and fix data defects across platforms
• Build and validate machine learning models for demand forecasting, scenario modeling, and prediction
• Build and maintain Python data pipelines for ETL, model training, and automated forecasting, working with Data Engineers
• Build "what-if" scenario planning models to test business assumptions such as demand, resource capacity, and cost
• Track project execution in P6 (Primavera) and other systems, compare plan to actual, and identify gaps, root causes, and trends
• Build automated tracking and data for executive dashboards that flag projects at risk
• Use LLMs and prompt engineering to build tools that automate workflows and support decisions
• Explain findings to technical and non-technical audiences, answer user questions about model outputs and data issues, and document model performance and data definitions

REQUIRED QUALIFICATIONS/SKILLS

• Python (pandas, numpy, scikit-learn, scipy) for data analysis, statistical modeling, and ML
• SQL: querying, joining tables, and reading complex queries
• Foundational to intermediate ML experience (scikit-learn, XGBoost) and model validation metrics (R², MAE, RMSE, cross-validation)
• Experience building scenario planning and forecasting models
• Statistical analysis: modeling, hypothesis testing, and experimental design
• Experience cleaning and merging messy data from enterprise sources (SAP, Salesforce, Databricks, ERP/CRM)
• Familiarity with LLMs and basic prompt engineering
• Ability to read existing dashboards, models, and SQL to understand data flows and business logic
• Clear communicator who can explain technical findings to non-technical audiences; fluent in English
• Analytical, curious, self-motivated, and comfortable working with global teams

Preferred

• P6 (Primavera), MS Project, or similar project execution systems
• Deep learning (TensorFlow, PyTorch) or advanced LLM work (RAG, fine-tuning, agents)
• MLOps and cloud experience (MLflow, Azure/AWS/GCP)
• Unit testing (pytest) and data governance or responsible AI knowledge

MUST HAVE

• Python (pandas, numpy, scikit-learn) for data analysis, statistical modeling, and ML development
• SQL: querying, joining, and interpreting complex queries
• Scenario planning and forecasting models
• Ability to translate complex data findings into clear business insights for non-technical audiences