United States
about 1 hourRemote, United States or Canada | Full-time | 2 Openings | Competitive salary
ABOUT OUR CLIENT
Our client is a leading provider of software for critical infrastructure, supporting oil & gas pipeline operators across North America with technology that improves the safety, reliability, and integrity of their assets.
THE OPPORTUNITY
If you want your work to make infrastructure smarter, safer, and more resilient, you’ll thrive here. Our client is building a new AI-driven threat and risk management platform for pipeline asset integrity, and is hiring Risk Model Engineers to own the transmission risk models on its analytical layer. Operators already run their probabilistic threat models in production. You’ll migrate those models to the new platform, extend coverage across the transmission threat set, and help build a model library whose outputs operators explain and defend to regulators.
Practical North American oil and gas transmission experience is the top priority, and strong industry candidates are encouraged to apply even if their modeling background is lighter. Two engineers are being hired, so one may bring deeper industry experience and the other deeper modeling expertise. This role is fully remote within the US or Canada, with working hours within about four hours of Central Time.
WHAT YOU’LL DO
Migrate probabilistic model code to the new risk management platform and validate against the existing implementation
Integrate model inputs from diverse inspection, sensor, maintenance, and operational datasets
Extend threat coverage across corrosion, cracking, third-party damage, outside forces, and other threats
Design and build time-series, anomaly detection, and geospatial models
Implement industry-standard probabilistic risk models and support customer-driven model development
Build, evaluate, and present robust sensitivity analysis for all model offerings
Validate model outputs against customer data, known outcomes, and regulatory scrutiny
Partner daily with ML Ops and data engineering, who own productionization, while you own the model content and the evidence that it’s right
WHAT YOU BRING
North American oil and gas transmission integrity experience, including ASME B31.8S, 49 CFR 192, CSA Z662, or equivalents
Fitness-for-service and remaining-strength assessment, corrosion growth modeling, or fracture mechanics
In-line inspection (ILI) data experience: vendor formats, alignment, anomaly classification, and feature disposition
Consequence-area and class-location analysis, and experience producing validation evidence for regulatory or audit review
Experience building or validating quantitative risk, reliability, or failure models for physical infrastructure (pipelines ideally; rail, structural, water, or utility assets transfer well)
Monte Carlo simulation, structural reliability, and uncertainty quantification methods
NICE TO HAVE
Machine learning on physical asset data (time-series, survival, anomaly detection, classification), especially on sparse, imbalanced failure events
Geospatial analysis with ArcGIS, PostGIS, or linear referencing
Sound Python engineering habits, including testing, code review, and disciplined use of AI coding assistants
You don’t need to check every box. Candidates with deep transmission industry experience or strong quantitative modeling expertise are encouraged to apply, especially if they bring working familiarity with the other area.
This posting may involve the use of AI tools to assist in reviewing applications; final hiring decisions are made by humans.
As part of our hiring process, this role may use artificial intelligence or automated tools to assist with reviewing and matching applications. These tools support, but do not replace, human judgment in making hiring decisions.
Please note that your application is only complete once you finish the registration process on the Keystone AI platform—including creating your profile, uploading your CV, and submitting your application. The AI interview is optional and encouraged, but it is not required for your application to be counted.
