{"html":"<h4>Role Overview</h4><p>We are seeking Earth Sciences experts to develop realistic, terminal-based scientific tasks for Terminal Bench Science. You will create computational workflows involving environmental data, climate systems, atmospheric processes, geophysics, oceanography, geology, and related fields.</p><p>You will design tasks that require AI agents to inspect scientific datasets, process geospatial or time-series data, run models, troubleshoot pipelines, and generate objectively verifiable scientific outputs.</p><h4>What you'll do</h4><ul><li><p>Translate authentic Earth-science workflows into self-contained terminal benchmark tasks.</p></li><li><p>Prepare geospatial, climate, atmospheric, geological, hydrological, or oceanographic datasets.</p></li><li><p>Build reproducible computational environments with appropriate scientific libraries and command-line tools.</p></li><li><p>Create expert solutions using Python, R, Bash, Julia, or domain-specific software.</p></li><li><p>Develop tasks involving geospatial analysis, time-series processing, numerical modeling, interpolation, forecasting, remote sensing, or environmental risk analysis.</p></li><li><p>Define objective grading criteria for scientific outputs, model behavior, data transformations, and spatial or temporal accuracy.</p></li><li><p>Validate coordinate systems, units, timestamps, missing-data handling, and scientific assumptions.</p></li><li><p>Create automated tests for numerical tolerances, file formats, metadata, and reproducibility.</p></li><li><p>Debug issues involving geospatial projections, large datasets, dependencies, performance, and numerical stability.</p></li><li><p>Document input data provenance, expected outputs, edge cases, and limitations.</p></li></ul><h4>What we're looking for</h4><ul><li><p>Ph.D., postdoctoral experience, or equivalent advanced technical experience in <strong>Earth Sciences or a closely related field</strong>.</p></li><li><p>Strong expertise in at least one area such as <strong>climate science, atmospheric science, geophysics, oceanography, geology, hydrology, remote sensing, environmental modeling, or Earth-system science</strong>.</p></li><li><p>Strong programming skills in <strong>Python, R, Julia, Bash</strong>, or another scientific programming language.</p></li><li><p>Hands-on experience with scientific data processing, numerical modeling, geospatial analysis, environmental datasets, or time-series analysis.</p></li><li><p>Comfortable working independently in <strong>Linux/terminal-based environments</strong>.</p></li><li><p>Ability to build, debug, and validate reproducible scientific computational workflows.</p></li><li><p>Strong understanding of scientific quality control, spatial/temporal data, uncertainty, and numerical accuracy.</p></li></ul><h4>Preferred Qualification</h4><ul><li><p>Experience with <strong>NumPy, pandas, SciPy, xarray, rasterio, GeoPandas, Cartopy, GDAL</strong>, or similar scientific/geospatial tools.</p></li><li><p>Experience with scientific data formats such as <strong>NetCDF, HDF5, GeoTIFF, shapefiles, or GRIB</strong>.</p></li><li><p>Experience working with climate, weather, satellite, seismic, oceanographic, geological, or hydrological datasets.</p></li><li><p>Familiarity with <strong>Docker, Conda, Git, CI/CD, automated testing, or HPC environments</strong>.</p></li></ul>Nice to Have:<ul><li><p>Research software engineering, scientific benchmarking, or automated grader development experience.</p></li><li><p>Experience evaluating AI coding/terminal agents or developing tasks and evaluations for AI systems.</p></li><li><p>Publications or open-source contributions in Earth, environmental, geospatial, or computational sciences.</p></li></ul><br><p>Offer Details:</p><ul><li><p>Commitments Required: At least 6 hours per day and minimum 40 hours per week with overlap of 4 hours with PST. </p></li><li><p>Employment type : Contractor assignment (no medical/paid leave)</p></li><li><p>Duration of contract : 5 week [expected start date is next week]</p></li><li><p>Payment type: Pay Per Task $300/per aproved task</p></li></ul>"}