Principal Data Scientist

Weyerhaeuser seeks a Principal Data Scientist to shape analytics strategy across our sustainable timberlands and manufacturing operations. You will lead development of advanced models that optimize mill performance, supply chain, and resource planning, using ML, statistics, and optimization at scale. Partnering with forestry, operations, and IT, you'll turn complex data into actionable insights that drive safety, efficiency, and environmental stewardship. You will mentor team members, champion data governance, and help advance innovative, sustainable wood products for North America.

Responsibilities

• Lead development of advanced predictive and optimization models to improve mill efficiency, yield, and quality across wood products operations
• Partner with forestry, manufacturing, and supply chain leaders to translate business challenges into data science solutions and measurable outcomes
• Design and implement scalable data pipelines and feature engineering in collaboration with data engineering and IT teams
• Apply machine learning, statistical modeling, and experimentation to forecasting, process control, and asset performance use cases
• Guide model deployment, monitoring, and lifecycle management in production environments
• Mentor data scientists and analysts, setting technical standards and promoting best practices in code quality and documentation
• Communicate insights and recommendations to senior leadership through clear visualizations and storytelling
• Ensure data governance, model ethics, and responsible AI practices aligned with sustainability and safety priorities
• Evaluate and integrate new data sources, including sensor, Io
• T, and spatial data from forest and mill operations
• Contribute to analytics strategy and roadmap to advance Weyerhaeuser's digital and sustainability goals

Required Skills

• Machine learning
• Statistical modeling
• Predictive analytics
• Optimization techniques
• Python
• RSQLBig data platforms (e.g., Spark, Databricks)
• Cloud analytics (e.g., AWS, Azure, GCP)
• Data engineering and pipelines
• Time series forecasting
• Experimental design and A/B testing
• Data visualization (e.g., Tableau, Power BI)
• MLOps and model deployment
• Sensor/Io
• T data analysis
• Supply chain and manufacturing analytics
• Version control (Git)
• Feature engineering
• Model monitoring and governance
• Communication and stakeholder management