Machine Learning Researcher

Rainmaker is pioneering a modern cloud-seeding system to increase precipitation, improve water availability, and address severe-weather challenges. We combine atmospheric science, weather-resistant UAS, radar and satellite observations, numerical weather prediction, novel sensing systems, and sustainable seeding technologies to design, operate, and evaluate precipitation-enhancement programs.

Research at Rainmaker is attached directly to operations. Our scientists and engineers collect proprietary observations, deliberately intervene in atmospheric systems, evaluate the results, and use what they learn to improve the next operation.

Rainmaker is hiring its first dedicated Machine Learning Researcher. You will establish how Rainmaker uses machine learning across the company: identifying the most valuable problems, determining which are ready for ML, building working models, and partnering with engineers and domain experts to turn successful research into operational systems.

You will not inherit a single predetermined model roadmap. The opportunity set includes forecasting supercooled liquid water and cloud-seeding opportunities, assimilating multimodal observations into estimates of atmospheric state, improving microwave-sounder retrievals, predicting hail, learning from intervention outcomes, and finding other high-leverage applications across research and operations.

Rainmaker's long-term advantage is not a generic weather model. It is the combination of proprietary in-cloud observations, radar and satellite data, UAS measurements, field campaigns, and repeated atmospheric interventions. You will build the learning systems that turn those data into better estimates, predictions, and decisions.

This is initially a hands-on individual-contributor role. You may eventually help recruit or technically lead an ML team if that fits your strengths and Rainmaker's needs, but management is not an initial expectation.

We care deeply about demonstrated technical ownership. If you have a project, system, experiment, paper, portfolio, or technical write-up that shows how you approach difficult problems, include it with your application and tell us what you personally contributed.

Rainmaker will provide a dedicated compute budget, access to observations from its sensor fleet, growing proprietary datasets from operations and field campaigns, and close collaboration with atmospheric scientists and software engineers.

The data will not always arrive in a polished benchmark. Part of the role is determining what can be learned now, what ground truth must be improved, and which new observations would most increase future model performance.

Within your first three months, you will have audited Rainmaker's most promising ML opportunities, selected a narrow and valuable initial problem, established a credible baseline, and delivered an operationally useful model or prototype with a concrete evaluation.

Within your first year, you will have established a prioritized ML roadmap grounded in actual data readiness and operational value; delivered one or more models that materially improve a scientific or operational workflow; and created reusable datasets, evaluations, or modeling foundations that accelerate subsequent work.