Data Scientist I

The Data Scientist I - Reliability and Maintenance Planning supports reliability, maintenance planning, and operational decision-making across Fleet and Equipment at TTX.

This role focuses on developing statistical and machine learning models to improve component reliability, optimize maintenance strategies, and enhance fleet performance. The position works with complex operational datasets (e.g., detector, movement, and billing data) and partners closely with Fleet, Engineering, Supply Chain, and other business stakeholders.

While the primary focus is reliability analytics, the role will also gain exposure to modern analytics platforms including Microsoft Fabric, Power Platform, and other AI-enabled solutions as part of TTX's evolving data ecosystem.

This role is ideal for candidates interested in applying data science to real-world operational and reliability challenges in an asset-intensive environment.

Responsibilities

• Reliability Modeling and Predictive Analytics (Primary)

• Develop and evaluate component failure and reliability models using statistical and machine learning techniques
• Apply and benchmark methods such as Weibull analysis, survival modeling, and predictive ML approaches
• Analyze operational datasets (detector, billing, movement/location) to identify failure patterns and risk drivers
• Support maintenance strategy optimization and predictive maintenance initiatives

• Business Partnership

• Partner with Fleet, Engineering, and Supply Chain stakeholders to translate business problems into analytical solutions
• Support benchmarking and evaluation of supplier performance and maintenance strategies
• Communicate insights clearly through dashboards, presentations, and documentation
• Gain strong working knowledge of rail industry and associated data including billing, detector, movement/location, etc.

• Data Analysis and Visualization

• Perform exploratory data analysis and feature engineering on complex, real-world operational datasets
• Clean and reconcile data across multiple systems and sources
• Develop reproducible datasets and modeling workflows
• Build Power BI dashboards and semantic models to deliver insights and support decision-making
• Assist in development of corporate metrics and program performance reporting

• Platform and Automation (Secondary)

• Contribute to automation of analytical workflows using Power Automate, PowerApps, or Python
• Gain exposure to Microsoft Fabric for data workflows and model integration
• Support development of AI-enabled solutions (e.g., Copilot Studio, Fabric Data Agents) as part of team initiatives

• Bachelor's degree in Data Science, Statistics, Engineering, Industrial Engineering, Business Analytics Asset Management, Artificial Intelligence, or related field

• 2+ years of professional experience in: o Data science, analytics, OR reliability/predictive analytics

• Experience with: o Python (pandas, scikit-learn or equivalent) o SQL for data extraction and transformation o PowerBI or other visualization tool o Messy, real-world operational data o Analysis of large, multi-source datasets

• Strong analytical and problem-solving skills

• Strong verbal and written communication skills

• Strongly Preferred

• Experience with: o Reliability modeling (Weibull, survival analysis, failure modeling) o Time series forecasting or predictive maintenance o Statistical modeling and hypothesis testing o Industrial, transportation, or asset-heavy data environment o PySpark and AutoML o Git/AzureDevOps and version control o Basic understanding of data engineering concepts like ETL pipelines and CICD

• Nice to Have

• Experience with: o Azure Dev Ops o Microsoft Fabric o Microsoft Power Platform (Copilot Studio, Power Automate, Power Apps) o Microsoft Foundry

• Knowledge and understanding of railcar data and reporting are strongly preferred such as industry detector data, billing, etc.