Model Engineer

This is a fully remote position, open to applicants in United States, +1 more country.

📋 Description

• Transition current probabilistic model code to the risk management platform.

• Verify the accuracy of migrated results in comparison to the existing implementation.

• Integrate model inputs from various datasets spanning Irth’s product range.

• Broaden threat coverage to include corrosion, cracking, third-party damage, external forces, and other risks associated with transmission pipelines.

• Design and develop time-series, anomaly detection, and geospatial models for inspection, sensor, and maintenance data.

• Implement Irth’s proprietary model library alongside the current model suite.

• Generate explainable and defensible risk outputs for pipeline operators and regulatory bodies.

• Manage model content, encompassing computations, rationale, and evidence to validate correctness.

• Collaborate closely with ML Ops and data engineering teams responsible for serving, pipelines, deployment, and monitoring infrastructure.

• Work in partnership with data engineering, ML Ops, data science, and subject-matter experts from conception through validated implementation.

• Assist in verifying the parity of existing models on the new platform.

• Implement and provide support for customer-developed models on the platform.

• Ensure that model outputs are reproducible and traceable.

⛳️ Requirements

• Proven experience in building or validating quantitative risk, reliability, or failure models for physical infrastructure.

• Pipeline experience is preferred; experience with rail, structural, water, electric, or other utility assets is also relevant.

• Knowledge of pipeline integrity standards and regulations, such as ASME B31.8S, 49 CFR 192, CSA Z662, or equivalent frameworks.

• Experience with fitness-for-service and remaining-strength assessments, corrosion growth modeling, or fracture mechanics.

• Familiarity with inline inspection (ILI) data, including vendor formats, data alignment, anomaly classification, and feature disposition.

• Experience with Monte Carlo simulation, structural reliability, and uncertainty quantification.

• Expertise in the application of machine learning to physical asset data, including time-series, survival, anomaly detection, and classification models trained and validated against sparse or imbalanced events.

• Experience in consequence-area and class-location analysis.

• Proficient in geospatial analysis, including tools such as ArcGIS, PostGIS, or linear referencing.

• Ability to produce model validation evidence suitable for regulatory, audit, customer, or other formal reviews.

• Strong software engineering practices, including testing, code review, reproducibility, and disciplined utilization of AI-assisted development tools.

• In-depth expertise in one or more of the listed capability areas, with the capacity to learn and collaborate across others.

🏝️ Benefits

• Competitive compensation package based on experience and qualifications.

• Medical, Dental, and Vision Insurance.

• 401(k) Plan with Company Match.

• Generous Paid Time Off (PTO).

• Company-Paid Holidays.

• Flexible Work Options.

• Work-from-home opportunities, subject to role and business requirements.

• On-Call Compensation for eligible on-call shifts.