Principal Data Scientist

Weyerhaeuser•Seattle, WA

1d•$131,082 - $196,766

About The Position

Grasp the opportunity to apply data science to the physical world of manufacturing! We are seeking an experienced Principal Data Scientist to provide technical leadership and passionate about applying machine learning, statistics, experimentation, and optimization techniques to solve complex business problems across manufacturing, operations reliability, supply chain, and product quality domains. We have a large manufacturing presence in North America with lumber, OSB, plywood, and engineered lumber products mills in Canada and the United States. Our Weyerhaeuser brand and scale of operations make us a major player in the wood products business. You would be partnering with our manufacturing mills to identify, analyze, and solve complex problems related to production quality, equipment reliability, and preventative maintenance. Your work would directly impact operational efficiency, improved product quality, and mill uptime. This role is responsible for shaping AI and ML strategy, defining reusable machine learning capabilities, leading complex experimentation, and delivering scalable solutions that create measurable business value. You have a high attention to detail, but are good at seeing the big picture, and aren’t afraid to think outside the box, and champion your ideas. You have experience articulating opportunity, as well as creating and successfully managing projects. You are effective at communicating timely and relevant information to business leaders and internal partners.

Requirements

10+ years of experience developing and deploying machine learning and AI solutions.
Strong software engineering skills in Python and modern ML frameworks.
Deep expertise in supervised learing, forecasting, optimization, statistical modeling, anomaly detection, model evaluation and experimentation methodologies.
Demonstrated success delivering enterprise-scale AI products from concept through production.
Experience leading highly ambiguous technical initiatives.
Proven ability to influence technical strategy across multiple teams and organizations.
Experience with experimentation and causal inference methods, including A/B testing, quasi-experimental designs, and counterfactual analysis.
Experience communicating insights using Power BI or Python-based visualization libraries such as Plotly and Matplotlib.
Experience with modern cloud platforms and data architectures, including AWS, Azure, Snowflake, and MLOps, CI/CD, and model lifecycle management.

Nice To Haves

Practical experience with Recommendation Systems, Pricing Optimization, and Computer Vision
Practical experience in Forestry Services or Wood Product manufacturing
Experience with Industrial Internet of Things and time-series manufacturing data

Responsibilities

Lead the design of scalable solutions across multiple business domains.
Establish reusable patterns, standards, and best practices for model development and deployment.
Lead and develop advanced machine learning, optimization, forecasting, generative AI, and decision intelligence solutions.
Define success metrics that balance model performance with business outcomes including revenue growth, operational efficiency, customer experience, safety, and risk reduction.
Partner with Product Managers and Operation teams to identify, prioritize, and frame business opportunities that can be solved with scientific framework.
Influence technical direction across multiple programs without direct authority.
Design, execute, and analyze online and offline experiments, including A/B testing, causal inference, and counterfactual analysis, to evaluate the impact of data science solutions on business outcomes.
Design, develop, and evaluate machine learning and deep learning models to solve forecasting, optimization, reliability, anomaly detection, and decision-support problems.
Design and implement statistical process control methods and anomaly detection techniques to proactively address quality issues in the manufacturing process.
Own the end-to-end model lifecycle, including feature engineering, training, validation, deployment, monitoring, retraining, and continuous improvement.
Establish standards for feature stores, model registries, inference services, observability, and governance.
Collaborate with software engineers, ML engineers, and data engineers to productionize models and integrate AI capabilities into business workflows.
Demonstrate the ability to apply data science and machine learning techniques across multiple domains (e.g., manufacturing, supply chain, pricing, logistics), abstracting core patterns, and adapting solutions to new problem spaces.
Translate ambiguous business problems into scientific approaches and influence stakeholders through data-driven recommendations.
Develop analytical visualizations and communicate findings through dashboards, notebooks, and presentations that drive business decisions.
Mentor junior team members and contribute to data science standards, reusable patterns, and best practices.