Machine Learning Researcher

About Rainmaker

Rainmaker Technology Corporation is innovating cloud-seeding technologies to boost precipitation and water availability while managing severe weather issues. They integrate atmospheric science, rugged UAS, radar/satellite data, weather prediction models, novel sensors, and sustainable seeding techniques to engineer, execute, and assess precipitation-enhancement operations.

At Rainmaker, research is tightly linked to practical operations as their scientists actively collect unique data, intentionally modify atmospheric conditions, analyze outcomes, and leverage their findings to refine future interventions.

Role Overview

The company is seeking their inaugural dedicated Machine Learning Researcher to define and implement ML strategies across their projects. The role involves identifying critical ML problems, prioritizing feasible tasks, creating prototypes, and collaborating with engineers and domain experts to transform research into deployed systems. Initial focus includes forecasting atmospheric variables related to cloud seeding, assimilating diverse data sources, enhancing microwave-sounder retrievals, hail prediction, intervention outcome analysis, and other impactful applications.

Responsibilities

• Evaluate and prioritize machine learning initiatives based on operational impact, data availability, technical feasibility, and timeline.
• Deliver an operational model or prototype within the first three months.
• Develop models for forecasting, nowcasting, retrieval, and multimodal atmospheric state estimation relevant to cloud-seeding.
• Forecast supercooled liquid water parameters critical to operations.
• Integrate public weather models and sensor data including radar, satellite, microwave-sounder, aircraft, UAS, sounding, and surface measurements.
• Create datasets, labels, evaluation metrics, and validation methods for variables not well captured by public systems.
• Perform rigorous experimental comparisons and analyze calibration, uncertainty, and failure modes.
• Collaborate closely with meteorologists and atmospheric scientists to define targets, constraints, and ground truths.
• Write research-grade software and build models that can be transitioned to production by engineering teams.
• Manage computational resources judiciously, scaling experiments only when justified.
• Support organizational learning from each operation, campaign, sensor deployment, and intervention.
• Communicate findings and limitations clearly to scientific and engineering teams as well as leadership.

Qualifications

• Demonstrated excellence in machine learning research and engineering, developed through academia, industry, independent work, or related technical fields.
• Proficient with contemporary machine-learning techniques and experienced in training, evaluating, and troubleshooting models.
• Strong Python programming skills and familiarity with ML frameworks such as PyTorch or JAX.
• Capable of translating ambiguous problems into quantifiable targets, credible baselines, and functioning prototypes.
• Experienced with statistical rigor addressing data leakage, distribution shifts, calibration, uncertainty, and bias.
• Comfortable handling noisy, sparse, multimodal spatial and temporal datasets.
• Preference for simple methods when adequate, reserving complex approaches for problems with clear benefits.
• Ability to collaborate with domain experts outside prior specialty.
• High initiative, rapid learning aptitude, and focus on impactful outcomes.

Preferred Experience

• Background in weather, climate, remote sensing, geospatial data, scientific machine learning, robotics, aerospace, or data-limited scientific domains.
• Experience with forecasting, sequence modeling, probabilistic or generative models, sensor fusion, or data assimilation.
• Handling radar, satellite, microwave-sounder, imagery, trajectory, gridded, or in-situ sensor data.
• Practical experience transitioning research models into production workflows alongside software engineers.
• Expertise designing data collection or labeling strategies where existing datasets are inadequate.
• Familiarity with atmospheric science is beneficial but not required.

Starting Resources

Rainmaker offers a dedicated compute budget, exclusive access to sensor data sets from proprietary fleets and campaigns, and collaborative support from atmospheric scientists and software developers. Data may require significant shaping, and thus assessing learning potential and improving ground truth are key parts of the role.

Success Metrics

Within three months, the researcher will have assessed ML opportunities, selected a valuable initial task, and delivered a working prototype or model with evaluation metrics. Within one year, they will have established a strategic ML roadmap anchored in data readiness and operational value, developed models enhancing scientific or operational processes, and established reusable data foundations to accelerate further work.

Benefits

• Ownership in the company via significant stock options with large growth potential.
• 401(k) plan with employer matching contributions.
• Comprehensive medical, dental, and vision insurance coverage.
• Relocation support, if applicable.
• Unlimited paid time off.
• Paid parental leave available to both parents.
• Complimentary lunch and well-stocked kitchen for in-office staff.
• Free electric vehicle charging at headquarters.