Key Responsibilities
Understand customer business and reliability objectives and translate them into Industrial AI / predictive analytics use cases. Analyze P&IDs;, PFDs, equipment design, operating philosophy, and performance/efficiency calculations to understand asset processes, operating boundaries, and failure behavior. Define and validate asset-to-tag relationships, ensuring relevant process, mechanical, and performance parameters are correctly mapped from DCS, SCADA, historians, and other data sources. Work with AI/ML and predictive analytics platforms to configure, deploy, and operationalize models for equipment health and performance monitoring. Apply engineering domain knowledge to interpret model outputs, anomalies, patterns, correlations, and early warnings and assess their operational relevance. Perform functional validation and quality assurance of analytics models by comparing model behaviour with equipment operating conditions, historical patterns, and known failure mechanisms. Support the development of AI/ML-driven monitoring approaches by providing equipment-domain knowledge, failure-mode understanding, and relevant feature/tag selection. Collaborate with Product, Project Management, Data Science, Engineering, and Technical Consulting teams to ensure solutions meet customer requirements. Identify opportunities to improve model effectiveness, monitoring workflows, automation, and deployment scalability. Develop reusable domain knowledge, validation methodologies, equipment templates, and best practices across predictive analytics implementations. Qualifications & Functional Skills Industrial Domain





Experience:
Robust understanding of rotating and/or process equipment, operating principles, performance characteristics, and common failure mechanisms. Predictive Maintenance & Reliability: Working knowledge of condition monitoring, predictive maintenance, RCA, FMEA, RCM, and equipment health assessment. AI/ML Familiarity: Good understanding of AI/ML concepts relevant to industrial applications, including anomaly detection, regression, classification, pattern recognition, time-series analytics, model training, validation, and performance evaluation. Predictive Analytics Platforms: Familiarity with industrial analytics/APM platforms such as GE SmartSignal, AVEVA PRiSM, Aspen Mtell, UptimeAI, Prometheus APM, Bently Nevada System1, or similar solutions. Engineering Documentation: Ability to interpret P&IDs;, PFDs, equipment datasheets, control philosophy, process calculations, and performance curves. Tag Mapping & Data Understanding: Ability to identify and map relevant sensor/process tags from DCS, SCADA, PLCs, and historians to analytics models. Model Validation: Ability to evaluate whether model outputs and detected anomalies are technically meaningful and consistent with actual equipment/process behavior. AI/ML Implementation Exposure: 2+ years of experience working with analytics solutions, AI/ML-based monitoring, predictive models, or rule-based diagnostic solutions for rotating machines in industrial environments. Cross-functional Collaboration: Ability to bridge the gap between domain engineering, customer requirements, data science, and technology teams.

📌 Industrial AI Engineer (India)
🏢 Alike Thoughts
📍 India