AI Ocean Carbon Flux Modeling Engineer

Paleon Data

Remote · $130k – $160k / year · Full-time · Posted 4 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Oceans absorb roughly 25% of anthropogenic CO2 emissions, but the rate and distribution of that absorption is poorly constrained. The uncertainty in global carbon budget estimates comes substantially from uncertainty in ocean-atmosphere carbon flux — and that uncertainty affects every policy decision about how aggressively to reduce emissions. We build climate data analytics infrastructure for 18 research institutions and government agencies. Ocean carbon flux modeling is one of the most data-rich, model-constrained problems in climate science: satellite SST, wind speed, chlorophyll concentration, salinity, and pH measurements from Argo floats all influence flux rates, but the mechanistic relationships are complex and the training data is spatially sparse. You'll build ML models that improve ocean carbon flux estimation: integrating multi-source satellite and in-situ observations, learning from oceanographic survey campaigns to improve global coverage, and quantifying uncertainty in flux estimates in a form that's useful for carbon budget calculations. You'll collaborate with oceanographers who'll provide scientific grounding and validate model outputs against physical plausibility constraints.

Fully remote.

Responsibilities

Design ocean carbon flux ML models integrating satellite and in-situ observation data sources
Implement spatial and temporal interpolation for flux estimation in data-sparse regions
Build uncertainty quantification providing calibrated flux estimate confidence intervals
Validate models against independent survey campaign data and physical plausibility checks
Develop flux trend analysis detecting changes in regional carbon uptake over time
Collaborate with oceanographers to ensure physical consistency of model predictions

Requirements

6+ years in environmental data science, oceanography ML, or geophysical modeling
Strong Python and statistical modeling skills with geospatial data experience
Familiarity with ocean carbon cycle dynamics and relevant data sources (SOCAT, Argo, satellite products)
Experience with uncertainty quantification in scientific ML applications
Ability to collaborate effectively with domain scientists