Rainmaker Fellow, Machine Learning

Examples of the Work

Fellowship projects change with Rainmaker's research and operational priorities. Examples of the work our ML team may pursue include:

- Developing a short-range supercooled liquid water opportunity forecast using public NWP and Rainmaker observations.

- Predicting hail-core growth, motion, splitting, and decay from radar sequences.

- Building a bounded multimodal atmospheric-state reconstruction pilot.

- Improving microwave-sounder retrievals using Rainmaker observations.

- Modeling another scientific or operational problem selected with Rainmaker's ML and atmospheric-science teams.

What You'll Do

- Translate a scientific or operational question into a measurable ML problem.

- Build or improve the training and validation dataset needed for the project.

- Establish simple, reproducible baselines before introducing more complex models.

- Train, evaluate, and debug models using held-out weather events, regions, or operating conditions.

- Quantify calibration, uncertainty, generalization, failure modes, and sensitivity to missing or biased data.

- Work closely with atmospheric scientists to define useful targets, ground truth, physical constraints, and operational success criteria.

- Produce clear, reusable code and documentation.

- Present your results to Rainmaker's scientists, engineers, operators, and technical leadership.

- Deliver a final artifact such as a benchmark dataset, model, prototype product, evaluation report, or research paper.

What We're Looking For

- Current undergraduate, master's, or PhD students; postdoctoral researchers; recent graduates; and other early-career researchers are all eligible.

- Strong Python programming ability and experience with a modern ML framework.

- Evidence that you can independently build, test, and debug technical work.

- Strong quantitative reasoning and an ability to design credible experiments.

- Interest in noisy, sparse, multimodal, spatial, temporal, or physical data.

- Ability to make progress on ambiguous research problems while incorporating mentor feedback.

- Clear written and verbal communication.

- Availability for full-time, on-site work in El Segundo for the agreed appointment.

Particularly Relevant Backgrounds

- Machine learning, computer science, applied mathematics, statistics, physics, meteorology, remote sensing, robotics, autonomy, geospatial analysis, or scientific computing.

- Forecasting, sequence modeling, computer vision, state estimation, sensor fusion, probabilistic modeling, data assimilation, or uncertainty quantification.

- Weather knowledge is valuable but not required.

What Success Looks Like

By the end of the fellowship, you will have answered a clearly defined technical question and produced a rigorous, reusable result that advances the team's work. Depending on the project, that might be a benchmark dataset, evaluated model, prototype product, forecasting or retrieval improvement, or a well-supported analysis of performance and failure modes.

Success does not require a positive scientific result. A well-supported finding that the available data cannot answer the question—and a concrete recommendation for what Rainmaker should measure next—can be highly valuable.

Fellowship Details

- Paid, full-time, and on-site in El Segundo.

- Three-to-six-month appointment, with four months as the standard duration.

- Rolling applications and flexible start dates based on project and mentor readiness.

- Possible consideration for future full-time roles, without any promise or expectation of conversion.

Compensation and Benefits

$8,000 per month

Benefits:

- Full health coverage (medical, dental, and vision insurance)

- Lunch provided when working in-office and a fully stocked kitchenette

- Free EV charging at the HQ