Predictive Analytics Engineer

Role overview

Core responsibilities

• Build predictive solutions for reliability monitoring, condition-based and predictive maintenance, failure prediction, and remaining useful life estimation.
• Develop supervised and unsupervised models, including regression, classification, clustering, anomaly detection, and time-series forecasting, using high-frequency sensor and operational data.
• Apply mathematics, statistics, and signal processing to feature engineering, model development, and optimization.
• Engineer scalable data and model pipelines with distributed and streaming technologies for historian, IoT, and maintenance data.
• Build physics-aware predictive and prescriptive models that account for equipment behavior and operating conditions.
• Work with engineers and subject matter experts to identify, validate, cleanse, and interpret historian, CMMS, inspection, and production records.
• Define analytical use cases and success criteria, and own initiatives from problem framing through deployment, adoption, and performance monitoring.
• Prototype in Python, R, or JavaScript; implement MLOps including CI/CD, automated testing, model versioning, containerization, monitoring, and drift management.
• Integrate dependable, explainable solutions with dashboards, alerting, and asset performance platforms while respecting operational and safety constraints.
• Communicate findings and recommendations to technical and non-technical audiences.

Education and experience

• Master’s degree in Computer Science, Mechanical Engineering, Statistics, Engineering, or an equivalent quantitative field.
• At least 10 years of hands-on experience designing, developing, deploying, and operating industrial predictive analytics and machine learning solutions.
• Mandatory experience in Oil & Gas or Manufacturing environments.
• Experience with predictive models for reliability monitoring, condition monitoring, and predictive maintenance, including regression, classification, anomaly detection, and time-series forecasting.
• Strong foundations in linear algebra, calculus, probability, and statistics applied to sensor, process, and equipment performance data.
• Expertise in industrial operations, asset integrity or performance management, process optimization, or maintenance and reliability engineering.
• Track record moving predictive models from prototype to sustained production use with measurable impact on uptime, maintenance cost, or production performance.
• Experience building scalable pipelines with distributed or streaming technologies such as Spark, Kafka, or MapReduce.
• Experience with process historians, SCADA/DCS, IoT platforms, and CMMS/EAM systems, and collaboration with cross-functional industrial stakeholders.
• Proficiency in Python, R, or JavaScript. Familiarity with Java or Scala is advantageous.
• Experience with version control, cloud platforms, and AI-assisted engineering workflows.