You will own the data from which we infer the subsurface, including what we acquire, how we represent it, and whether a model can rely on it. The central problem is heterogeneity. Gravity, magnetics, electromagnetics, seismic, geochemical assays, drill-core scans, geological maps and satellite spectra each measure a different property, at a different scale, through different physics and with different errors. We want to model these properties of the measurements, not clean them away. Ground truth is also scarce: only a few deposits are well documented.
What your first year looks like
- Define the canonical representation of an observation: geometry, support, units, uncertainty, instrument, provenance and lineage.
- Hire and lead a team of data engineers and data scientists.
- Lead the team to build a versioned subsurface data platform with provenance.
- Own the acquisition strategy: national geological survey archives, open airborne geophysics and geochemistry, satellite missions, and licensed company data (drillholes, assays, core scans), including the licensing and partnerships behind them.
- Establish QA/QC for censored assays, inter-laboratory effects and inconsistent vocabularies.
- Build the benchmark suite with the research team. This should include spatially blocked test regions and held-out deposits that keep evaluation honest.
You have:
- 5+ years of experience in data engineering or data science on scientific data. Geospatial or Earth observation data is strongly preferred, but we are open to experts across data-driven natural science research.
- A strong background in statistics, with a fair understanding of measurement error, censored data, spatial correlation and selection bias.
- A record of building ML-ready datasets that research teams trusted and used.
- Experience with cloud data lakes and orchestration.
- Fluency with research tools and formats, or the ability to pick them up. These include COG, Zarr, STAC, PostGIS, xarray, LAS and ASEG-GDF.
Nice to have:
- A background in geology, geophysics or geochemistry.
- Experience with drillhole databases, assay QA/QC and JORC or NI 43-101 reporting.
- Experience negotiating data partnerships with mining companies or geological surveys.
- Experience leading a team or being the first data hire.
Interested? Write to us at gondwana@altcarbon.com with the role in the subject line.