Space Operations Risk Assessment Specialist

University of North Dakota•Grand Forks, ND

1d•$20•Hybrid

About The Position

The UND Computational Research Center is seeking a risk assessment specialist with expertise in statistical risk assessment, failure probability analysis, and Bayesian statistical methods capable of translating this expertise into spacecraft failure prediction and uncertainty quantification. This position will work with a larger research team to develop AI models for predicting spacecraft failure.

Requirements

Demonstrated understanding of statistical risk assessment and failure probability analysis.
Strong problem-solving skills and attention to detail
Excellent written and verbal communication skills
Bachelors of Science degree in Actuarial Science, Mathematics, or a related field.
Experience programming using R, Python, and/or MATLAB
Experience developing Monte Carlo simulations
Compliance with U.S. government export control laws and regulations. Applicants are required to be eligible for employment under U.S. export control laws and must meet the requirement of being a “U.S. Person” (U.S. citizen, lawful permanent resident, or protected individual as defined by 8 U.S.C.1324b (a)(3)).
Successful completion of a Criminal History Background Check

Nice To Haves

Masters of Science degree in Actuarial Science, Mathematics, or a related field.
Experience with Bayesian statistical methods
Experience modeling rare, catastrophic failure events
Experience developing AI models for assessing risk and failure prediction.
Experience assessing risk and failure prediction for systems in remote, extreme physically inaccessible locations, such as a deep-sea environment or low-earth orbit.
Experience using the GitHub collaborative software development platform.

Responsibilities

Conduct a literature review on Bayesian network applications in spacecraft reliability, failure analysis, and risk assessment
Collect and curate failure data from relevant sources (e.g., spacecraft anomaly databases, mission reports, component reliability handbooks)
Identify key failure modes, subsystems, and causal relationships to be represented in the Bayesian network
Develop the network structure, including defining nodes, states, and dependencies in consultation with domain experts
Elicit and estimate conditional probability tables from data, expert judgment, or hybrid approaches
Implement and validate Bayesian network models using appropriate software (e.g., GeNIe, Netica, pgmpy, bnlearn)
Perform inference, sensitivity analysis, and scenario testing to evaluate failure probabilities and identify critical contributors
Document modeling assumptions, data sources, and limitations clearly and reproducibly
Present results through regular progress meetings, written reports, and visualizations
Contribute to manuscripts, conference papers, or technical reports as appropriate
Collaborate with team members and incorporate feedback into iterative model refinement