Risk Model Engineer - Pipeline Integrity (Transmission)

Risk Model Engineer — Pipeline Integrity (Transmission)

We don’t expect a single candidate to bring all of the experience listed below. North American oil and gas transmission experience is our highest priority. We’re hiring two engineers and will balance the team’s strengths across industry expertise and quantitative modeling. Candidates with deep practical industry experience or strong risk modeling expertise are encouraged to apply, provided they have working familiarity with the other area.

• Transmission pipeline integrity and regulation: Experience with North American oil and gas transmission integrity management, including applicable standards and regulations such as ASME B31.8S, 49 CFR 192, CSA Z662, or equivalents.
• Fitness-for-service and failure mechanisms: Familiarity with fitness-for-service and remaining-strength assessments, corrosion growth modeling, or fracture mechanics.
• In-line inspection (ILI) data: Experience working with ILI vendor data formats, data alignment, anomaly classification, and feature disposition.
• Consequence and location analysis: Experience with high-consequence areas, class-location analysis, or related pipeline risk assessment requirements.
• Regulatory and audit support: Experience preparing technical documentation and validation evidence for regulatory review, audits, or other formal assessments.
• Quantitative risk and reliability modeling: Experience building or validating risk, reliability, or failure models for physical infrastructure. Pipeline experience is ideal, but relevant experience with rail, structural, water, or utility assets can transfer well.
• Probabilistic methods and uncertainty: Familiarity with Monte Carlo simulation, structural reliability, uncertainty quantification, or related probabilistic methods.
• Machine learning and physical asset data: Experience applying machine learning to time-series, survival, anomaly detection, or classification problems involving physical asset data. Experience training and validating models on sparse, imbalanced failure events is particularly valuable. We’re especially interested in candidates who are strong in either machine learning or pipeline integrity and have working familiarity with the other.
• Geospatial analysis: Experience with ArcGIS, PostGIS, linear referencing, or geospatial risk assessment.
• Python and software engineering: Sound engineering practices, including testing, code review, reproducibility, and disciplined use of AI coding assistants.
• Real-world data and model judgment: Comfort working with incomplete, inconsistent, and imperfect data, along with the judgment to distinguish a defensible, validated model from one that simply produces a number.

You don’t need to check every box. We value sound technical judgment, practical industry knowledge, and the ability to build or validate models whose results can be explained and defended. We’re particularly interested in candidates who bring deep transmission expertise or strong quantitative modeling skills and can collaborate effectively across both domains.