Predictive Analytics Engineer

About the role

The Predictive Analytics Engineer designs, builds, and deploys advanced analytics solutions that improve asset reliability and enable predictive maintenance in complex Oil & Gas or manufacturing environments.

Key responsibilities

• Develop and tune supervised and unsupervised models for anomaly detection, failure prediction, remaining useful life estimation, and process optimization using high‑frequency sensor and operational data.
• Engineer scalable data and model pipelines with distributed and streaming technologies such as Spark, Kafka, and MapReduce to handle large volumes of process historian, IoT, and maintenance data.
• Collaborate with reliability, process, and maintenance engineers to translate operational problems into analytical use cases, validate data sources, and embed solutions into day‑to‑day operations.
• Implement MLOps practices, including CI/CD pipelines, automated testing, model versioning, containerisation, and production monitoring to ensure reliable, explainable, and production‑ready models.

Required profile

• Minimum 10 years of hands‑on experience designing, deploying, and operating predictive analytics or machine‑learning solutions in an industrial setting.
• Proven domain expertise in Oil & Gas or manufacturing, with strong understanding of asset performance management, process optimisation, and maintenance engineering.
• Advanced degree (MS) in Computer Science, Engineering, Statistics or a related quantitative field.

Required skills

• Proficiency in Python, R, or JavaScript (experience with Java or Scala is a plus).
• Experience with big‑data frameworks such as Spark, Kafka, and MapReduce.
• Strong mathematical and statistical foundation (linear algebra, calculus, probability, signal processing).
• Hands‑on knowledge of MLOps tools, CI/CD pipelines, containerisation, version control and cloud platforms.