Data Scientist [AQ-15925]

About the role

This is a greenfield project offering creative freedom to design and implement innovative AI solutions that will revolutionize how manufacturing data is utilized. You will have access to a wealth of manufacturing and quality data to build sophisticated data models and AI applications that enhance safety, quality, throughput, cost-efficiency, and equipment reliability. Your work will directly impact production lines, product quality, and operational efficiency across numerous facilities.

Responsibilities

• Translate complex operational and business challenges into measurable analytical questions and actionable use cases.
• Identify, access, and critically assess data from diverse manufacturing sources, including operational execution systems, quality systems, equipment historians, and maintenance platforms.
• Design and build robust analytical datasets and scalable data pipelines using industry-leading tools such as SQL, Python, Spark, and Databricks.
• Conduct in-depth exploratory analysis, statistical studies, root-cause investigations, forecasting, optimization, and experimentation to drive data-driven decisions.
• Develop, rigorously validate, document, and continuously monitor predictive or prescriptive models for critical use cases like downtime prediction, scrap reduction, defect detection, bottleneck identification, anomaly detection, yield optimization, and preventive maintenance.
• Evaluate data quality, lineage, coverage, potential missingness, bias, and overall operational readiness before model deployment.
• Transform complex analytical findings into clear, practical recommendations that empower plant personnel and leaders in their daily decision-making.
• Create intuitive dashboards, compelling visualizations, comprehensive reports, and user interfaces that effectively communicate trends, risks, and opportunities.
• Collaborate with data engineering, application development, and operational technology teams to successfully productionize analytics and models.
• Monitor model performance, detect data drift, ensure pipeline health, and track business impact post-deployment.
• Support strategic modernization initiatives, including cloud migration, data-product development, automation, and the retirement of legacy systems.
• Adhere to strict data governance, cybersecurity, AI governance, safety, privacy, and change-management requirements.
• Present complex technical results to both technical and non-technical audiences, maintaining clear and thorough documentation.
• Champion reusable analytical methods, standards, and best practices across various manufacturing domains.

Requirements

• A Bachelor’s degree in a technical field such as Computer Science, Computer Engineering, or a related discipline.
• At least 8–10 years of professional experience, with a significant focus on data.
• Extensive experience (8–10 years) in data modeling and designing and implementing effective data structures.
• Proven expertise (8–10 years) in building and managing robust data pipelines.
• Demonstrated ability (8–10 years) in data analytics, specifically extracting meaningful insights and building solutions from complex and often messy data.
• Proficiency in programming languages and tools such as SQL, Python, Spark, and Databricks.
• Strong background in applying statistics, machine learning, and optimization techniques.
• Excellent communication skills, capable of presenting technical information to diverse audiences and fostering collaboration across teams.
• Legal eligibility to work in the United States without employer sponsorship.

Qualifications

• Experience with application AI platform skill sets.