Asset Analytics Engineer – Smart Signal & Predictive Modelling
This role focuses on mapping historian tags to the SmartSignal Standard Data Model and orchestrating data for predictive model training. The engineer will build and maintain digital twins using similarity-based and empirical modeling techniques to ensure scalable, noise-free reliability analytics.
Skills required
About this role
Focus: Tag Mapping, Model Training, and Analytics Lifecycle Management
Role Overview: The Analytics Engineer is responsible for the end-to-end technical deployment of predictive models. Leveraging the Smart Signal platform (or equivalent), you will transform raw historian data into high-fidelity digital twins. Your focus is on the "Digital Architecture" of reliability—ensuring models are accurate, noise-free, and scalable.
Core Responsibilities:
- Data Orchestration & Tag Mapping: Perform complex mapping of historian tags (PI, OPC, IP21) to the SmartSignal Standard Data Model. Ensure data lineage and quality across fleet-level deployments.
- Model Training (SBM): Utilize Similarity-Based Modeling (SBM) and Empirical Model Learning (EML) to establish "Normal" operating profiles. Select high-quality training windows (Gold Standard data) that represent healthy asset states.
- Analytic Blueprinting: Develop and maintain "Analytic Blueprints" (templates) for common industrial classes such as pumps, motors, and transformers to enable rapid scaling.
- Model Maintenance & Tuning: Monitor model performance (Precision/Recall). Perform "Retraining" following asset overhauls or upgrades and tune statistical thresholds to minimize false positives.
Work Experience
Technical Skill Set:
- Programming: Proficient in Python for data manipulation (Pandas, NumPy) and building custom analytic rules/features.
- Platform Expertise: Hands-on experience in SmartSignal (GE Vernova), Aspen Mtell, or AVEVA PRiSM. Deep understanding of "Blueprints" and "Weekly/Monthly Model Review" workflows.
- Data Systems: Strong SQL skills for querying CMMS (Maximo, SAP PM) and Historian databases.
- Software: Familiarity with pulling data from APIs using Postman or similar tools, ability to work efficiently big excel and csv files.
• Strong analytical, debugging, and problem-solving skills.
• Excellent verbal and written communication skills with the ability to work effectively in cross-functional teams.
• Must have hands-on experience with Docker for containerizing, deploying, and managing applications.
• Understanding of DevOps practices, including CI/CD pipelines and container based deployment strategies.
Similar open roles
Operations Excellence and Supply Chain Analytics Lead
Product & Transaction Analytics - Fintech Client Risk Analytics, VP
