Scientific Computing / Research Engineering Expert

About the Role

• We are seeking experienced Earth Sciences experts to develop realistic, terminal-based scientific and computational tasks for a frontier AI training and evaluation initiative.
• In this role, you will design challenging scientific tasks involving climate science, atmospheric processes, geophysics, oceanography, geology, hydrology, remote sensing, and environmental modeling.
• You will build reproducible computational workflows that require AI agents to analyze scientific datasets, execute code, run simulations, troubleshoot technical issues, and generate objectively verifiable scientific outputs.

Key Responsibilities

• Design realistic, multi-step scientific tasks based on authentic Earth Sciences, climate, geospatial, environmental, and geophysical research workflows.
• Prepare and process scientific datasets involving climate, weather, atmospheric conditions, oceanography, geology, hydrology, satellite imagery, and environmental systems.
• Develop computational tasks involving geospatial analysis, time-series processing, numerical modeling, interpolation, forecasting, remote sensing, and environmental risk analysis.
• Build reproducible, terminal-based computational environments using scientific libraries, command-line tools, and appropriate dependencies.
• Develop expert reference solutions using Python, R, Bash, Julia, or domain-specific scientific software.
• Create automated tests and evaluation criteria to verify scientific correctness, numerical accuracy, spatial and temporal consistency, and reproducibility.
• Validate coordinate reference systems, measurement units, timestamps, missing-data handling, uncertainty, and scientific assumptions.
• Troubleshoot technical issues involving geospatial projections, large scientific datasets, software dependencies, computational performance, and numerical stability.
• Ensure tasks require meaningful multi-step scientific reasoning and cannot be solved through simple shortcuts or hard-coded outputs.
• Document dataset sources, computational workflows, expected outputs, edge cases, and scientific limitations.

Requirements & Tech Stack

• Ph.D., postdoctoral experience, or equivalent advanced technical experience in Earth Sciences, Climate Science, Atmospheric Science, Geophysics, Oceanography, Geology, Hydrology, Environmental Science, or a closely related discipline.
• Strong programming skills in Python, R, Bash, Julia, or another relevant scientific programming language.
• Hands-on experience working in Linux and terminal-based computational environments.
• Practical expertise in at least one major area: scientific data processing, numerical modeling, geospatial analysis, climate modeling, remote sensing, or environmental data analysis.
• Strong understanding of spatial datasets, time-series analysis, scientific modeling, numerical accuracy, uncertainty, and data quality control.
• Experience working with real-world scientific datasets, including geospatial, climate, atmospheric, oceanographic, geological, or hydrological data.
• Ability to independently develop, execute, debug, and validate reproducible scientific computational workflows.
• Strong analytical and problem-solving skills with the ability to identify scientific inaccuracies, data inconsistencies, and computational errors.
• Ability to design objective validation methods and clearly document technical solutions and scientific assumptions.

Nice to Have

• Experience with scientific computing and geospatial libraries such as NumPy, pandas, SciPy, xarray, rasterio, GeoPandas, Cartopy, GDAL, or similar tools.
• Familiarity with scientific data formats such as NetCDF, HDF5, GeoTIFF, shapefiles, GRIB, and other geospatial or environmental data formats.
• Experience working with climate, weather, oceanographic, seismic, satellite, hydrological, or geological datasets.
• Familiarity with Docker, Conda, Git, CI/CD pipelines, and automated testing frameworks.
• Experience using high-performance computing (HPC) environments or processing large-scale scientific datasets.
• Experience with Earth-system models, environmental forecasting, remote sensing applications, or geophysical simulations.
• Research software engineering experience, including developing scientific tools, simulation pipelines, or reproducible research workflows.
• Experience developing or evaluating AI coding agents, terminal-based agents, scientific benchmarks, or automated grading systems.
• Publications, research contributions, or open-source development experience in Earth or Environmental Sciences.
• Prior experience in AI training, scientific quality control, benchmark development, or evaluation programs.

Offer Details

• Commitments Required: At least 4 hours per day and minimum 40 hours per week with overlap of 4 hours with PST.
• Employment type: Contractor assignment (no medical/paid leave)
• Duration of contract: 4 weeks (expected start date is next week)