Senior Data Scientist - Predictive Maintenance & ML Ops

• Raleigh
  - North Carolina
  - United States of America

Description:

We are looking for a hands-on Data Scientist to transform asset, maintenance, operational, and product data into production-ready analytical and machine learning solutions.

In this role, you will partner with product managers, engineers, domain experts, and customer-facing teams to frame business problems, prepare data, develop and evaluate models, and support deployment into production workflows.

You will independently own well-defined data science work streams and be accountable for the quality, explainability, and measurable impact of your work. This role is ideal for someone with strong applied statistics, Python, SQL, and machine learning experience who can move effectively from exploration and experimentation to validated, production-ready solutions.

Location:

This position is remotely based within the United States.

However, to facilitate onboarding and establish key relationships with the team, the successful candidate will be required to attend their first week of employment onsite in Raleigh, NC. Following onboarding, the role will be fully remote.

Qualified Applicants must be legally authorized for employment in the United States and will not require employer sponsored work authorization now or in the future for employment in the United States.

You'll Make an Impact By:

Applied Data Science and Machine Learning

• Translate customer, product, and operational problems into clear analytical questions, hypotheses, modeling approaches, and measurable success criteria.
• Explore, clean, validate, and combine structured, time-series, sensor, work-order, inspection, and unstructured data.
• Develop and evaluate statistical and machine learning models for use cases such as forecasting, anomaly detection, asset condition assessment, failure prediction, predictive maintenance, and decision support.
• Select appropriate baselines, features, algorithms, validation strategies, and performance metrics based on business objectives and data characteristics.
• Perform error analysis, sensitivity analysis, and model interpretation to understand model performance, reliability, and limitations.
• Build explainable outputs that product teams, domain experts, and customers can understand and act upon.

• Apply statistical methods, hypothesis testing, and experimental or quasi-experimental techniques to evaluate product and model impact.
• Define baseline measures and compare model-driven approaches against existing processes or business rules.
• Partner with stakeholders to identify adoption measures, operational KPIs, and business outcomes.
• Communicate findings, assumptions, tradeoffs, and recommendations to both technical and non-technical audiences.
• Monitor whether deployed solutions continue to deliver intended customer and business value.

• Apply statistical methods, hypothesis testing, and experimental or quasi-experimental techniques to evaluate product and model impact.
• Define baseline measures and compare model-driven approaches against existing processes or business rules.
• Partner with stakeholders to identify adoption measures, operational KPIs, and business outcomes.
• Communicate findings, assumptions, tradeoffs, and…