Principal Data Scientist

1. The Principal Data Scientist will lead Data Science for Asset Reliability and Cognition portfolio to innovate and mature prognosis models for industrial equipment s, models to optimize maintenance strategies, and reduce operational risk.
2. This role requires a blend of machine learning expertise, reliability engineering knowledge, and oil gas domain experience to drive measurable impact across critical assets.
3. Also required is a customer-oriented focus by acknowledging their needs and offering pragmatic customer solutions that align with their data capabilities.

Qualifications

1. PhD or Master s in Data Science, Reliability Engineering, Chemical/Mechanical Engineering, or Applied Mathematics.
2. 12+ years of industrial analytics experience, with at least 5 years in oil gas reliability.
3. Expertise in time-series forecasting, reinforcement learning, graph neural networks.
4. Proficiency in Python, R, Scala, Spark, Hadoop, and cloud-native ML platforms (Azure ML, AWS SageMaker, GCP Vertex AI).
5. Familiarity with asset reliability standards.
6. Experience in risk-based inspection (RBI), HAZOP analytics, and probabilistic reliability modeling.

Focus Area Contribution:

1. Asset Reliability: Extend asset life cycles and reduce catastrophic failures.
2. Operational Excellence: Integrate ML with process simulators for refinery-wide optimization.
3. Cost Reduction: Deliver multimillion-dollar savings via predictive maintenance and inventory optimization.
4. Safety ESG: Enhance compliance and reduce environmental incidents through proactive monitoring.
5. Digital Transformation: Champion AI adoption across enterprise reliability programs.

Key Responsibilities

1. Predictive maintenance: Design and deploy ML models to forecast equipment failures and optimize maintenance schedules.
2. Digital twin development: Build hybrid AI + physics-based models to simulate asset health and performance.
3. Advanced anomaly detection: Implement deep learning and unsupervised methods for early detection of vibration, corrosion, and fouling.
4. Reliability analytics: Apply Bayesian networks, causal inference, and probabilistic modeling to identify root causes of failures.
5. Cross-functional leadership: Mentor data science teams, collaborate with engineers, and influence executive stakeholders.
6. Research and maintain a deep knowledge of the industry, including trends and technologies to identify strategy opportunities and contribute to thought leadership best practices.