Environmental AI Benchmark Engineer
Posted Updated
Description
Crossing Hurdles seeks experts to design realistic earth-science tasks that push advanced AI models, with a focus on reproducible environments and robust evaluation criteria. Applicants will develop reference solutions and benchmarks for geospatial analyses, simulations, and forecasting.
The role requires hands-on Python expertise and deep knowledge in earth or environmental science, plus experience benchmarking AI systems on scientific tasks.
Create realistic computational earth-science tasks that challenge advanced AI models. Develop task instructions, reproducible environments, reference solutions, and evaluation criteria. Evaluate model-generated code, geospatial analyses, simulations, forecasts, and technical deliverables. Identify issues involving coordinate systems, spatial or temporal data, model assumptions, uncertainty, numerical methods, or reproducibility. Prior paid experience training, evaluating, benchmarking, or improving AI systems on scientific or technical tasks. Strong practical proficiency with Python. Deep expertise in at least one relevant earth or environmental-science specialization. Hands-on experience using computational methods for geospatial analysis, modeling, forecasting, remote sensing, statistics, or reproducible research.Skills
Sign in to read and join the discussion.