Data Scientist #26-18742

$50-$54 per hour

Greenville, SC

Contract

Duration: 12
Months

Hybrid

• Client is accelerating the path to more reliable, affordable, and sustainable energy, while helping our customers power economies and deliver the electricity that is vital to health, safety, security, and improved quality of life.

• We are seeking a curious, analytically sharp, and digitally passionate Data Scientist to join our HDPE Operations & Strategy team - a team where collaboration and participative leadership are not just words, but the way we work every day. This is your opportunity to create real impact from day one. As a core member of our HDPE team, you will be at the forefront of our engineering vision — where data intelligence and AI-powered tools redefine how we manage, predict, and operate across Client's global business.

• You will act as the critical bridge between our Engineering domain data knowledge, business planning, operations and our IT execution team — defining what data we need, how it should be structured and used, and what AI/ML solutions can unlock the most value. You will support centralized business operations and program reporting that delivers harmonized insights and predicted range of outcomes to business stakeholders worldwide.

• You will build scenario planning models that test critical business assumptions and track project execution through P6 and enterprise systems, identifying gaps between plan and reality to drive proactive decision-making. This role will be critical in efforts to optimize HDPE Operations program management activities

• Python:
  Strong proficiency in data analysis, statistical modeling, and ML development (pandas, numpy, scikit-learn, scipy, curve fitting, object-oriented programming)

• Scenario Planning & What-If Analysis:
  Ability to build multi-scenario models to test assumptions and evaluate alternative planning outcomes

• Machine Learning:
  Foundational to intermediate experience with ML frameworks and methodologies (scikit-learn, XGBoost, or similar)

• Model Evaluation:
  Understanding of model validation metrics (R², MAE, RMSE, cross-validation, custom scoring functions)

• SQL:
  Proficiency in querying, joining tables, data manipulation, and interpreting complex queries

• Statistical Analysis:
  Understanding of statistical modeling, hypothesis testing, and experimental design

• Data Exploration:
  Ability to independently explore enterprise datasets and identify patterns, gaps, and opportunities

• Data Cleaning:
  Experience handling messy data, identifying inconsistencies, and standardizing formats across heterogeneous systems

• Data Integration:
  Experience merging multiple datasets from various enterprise data sources (SAP, Salesforce, Databricks, ERP/CRM)

• Anomaly Detection:
  Sharp eye for finding outliers, errors, and unusual patterns in structured and unstructured data

• Semantic Data Models:
  Understanding of data modeling concepts across heterogeneous systems

• Forecasting & Prediction:
  Experience developing models for scenario modeling and predictive use cases

• Large Language Models (LLMs):
  Familiarity with LLMs and basic prompt engineering techniques for practical business applications

• Dashboard & Logic Comprehension

• Reverse Engineering:
  Ability to review existing dashboards, ML models, and reports to understand design patterns, business requirements, and underlying data sources

• SQL Query Analysis:
  Strong capability to read and interpret complex SQL queries to understand data flows and business logic

• Data Source Understanding:
  Skills to trace data lineage, review prepared data sources, and comprehend underlying data structures

• Pipeline
  
  Collaboration:
  
  Experience working with Data Engineers to ensure data requirements are correctly implemented at pipeline and infrastructure level

• Advanced ML/Deep Learning:
  Experience with Tensor Flow, PyTorch, neural networks, or deep learning applications

• Unit Testing: pytest or similar frameworks for data science code quality

• Experience with P6 (Primavera), MS Project, or similar project execution systems

• MLOps:
  Model versioning, experiment tracking…