Analytics & Modeling Analyst (Inland Flood)

Role overview

Skills and competencies

• Strong foundation in hydrology, hydraulics, climate science, applied mathematics, data science, computer science, or a related quantitative discipline.
• Understanding of machine learning fundamentals, including model training and validation, overfitting, and model evaluation.
• Experience with one or more machine learning or deep learning approaches, such as LSTM networks, CNNs, and frameworks including PyTorch.
• Practical Python programming experience and familiarity with scientific computing environments.
• Experience with R, C/C++, Fortran, CUDA, or Bash is preferred.
• Ability to analyze, validate, and interpret large geospatial, hydrological, and climate datasets using statistical methods and visualization.
• Strong communication and collaboration skills, including explaining technical concepts to multidisciplinary stakeholders.
• High-performance computing, GIS, SQL, or data assimilation experience is desired.
• Basic AI understanding, curiosity about AI-enabled process improvement, and growing awareness of AI risk management and responsible, ethical AI use.

Education

• PhD in hydrology, hydraulics, coastal and ocean engineering, climate science, applied mathematics, data science, computer science, or a related quantitative discipline.
• Candidates with a relevant MSc and strong research or industry experience are also encouraged to apply.

Model development and analysis

• Contribute to flood hazard model components, including stochastic rainfall generation, rainfall-runoff, hydraulic routing, floodplain inundation, and flood defense failure mechanisms.
• Calibrate and validate model components using observed datasets, benchmark studies, and published research.
• Analyze flood footprints, hazard metrics, and loss patterns using statistics, geospatial tools, and visualization.
• Research and implement scientific and computational approaches to advance flood hazard modeling.

AI, workflows, and collaboration

• Prototype and assess AI and machine learning methods for surrogate modeling, spatial downscaling, anomaly detection, feature extraction, emulator development, and workflow automation.
• Develop and maintain reproducible scientific workflows, data processing pipelines, and code repositories using modern software development practices.
• Collaborate with scientists, engineers, and data specialists on model development, quality assurance, and scientific innovation.
• Present research findings and modeling insights to stakeholders, clients, and the scientific community through reports and technical discussions.