AI Weather Scientist

Pravāh • San Francisco, CA

3d

About The Position

Pravah is building foundational intelligence for the electric grid, applying modern machine learning to complex physical infrastructure problems spanning grid operations, weather, and geospatial systems. Our work sits at the intersection of computer vision, physical systems, and large-scale ML, with deployments across utilities in the United States and India. We leverage multimodal data - including satellite imagery, LiDAR, and street-level data - to build high-fidelity representations of grid assets and their surroundings. We are backed by Khosla Ventures, Pear VC, and Conviction.

The role involves advancing the next generation of weather forecasting systems. The AI Weather Scientist will work closely with machine learning and software engineers on four core threads: running numerical weather prediction models to generate high-resolution forecasts and training data; informing the development of AI weather forecasting models and innovating on existing architectures; evaluating pre-trained global and regional models against reanalysis, satellite, and ground observations to identify areas for improvement; and procuring, processing, and creating ML-ready global and regional weather datasets, with explicit focus on data-sparse regions.

Requirements

• A master's or PhD in geophysical sciences, physics, applied mathematics, computer science, statistics, or a related field. A bachelor's with 7+ years of relevant research or operational experience is also acceptable.
• Demonstrated depth in either numerical weather prediction, meteorology, or earth system modeling through research projects, publications, model contributions, or operational work.
• Experience working with high-dimensional observational and modeling datasets (reanalysis products, satellites, weather stations) in forecasting.
• Experience working with deep learning models and familiarity with at least one framework (PyTorch, JAX, or TensorFlow).
• Excellent written and verbal communication, including the ability to explain technical work to both domain experts and cross-disciplinary collaborators.

Nice To Haves

• Hands-on experience with high-resolution regional earth-system models such as WRF or MPAS, including dynamical cores, physics parameterizations, boundary-layer and convection schemes, or coupled ocean–atmosphere configurations.
• Experience with operational forecasting models or workflows (real-time data ingest, verification, cycling, product generation).
• Experience with either of data assimilation, ensemble and probabilistic forecasting, convection-permitting or mesoscale modeling, regional downscaling, or subseasonal-to-seasonal (S2S) prediction.
• Experience using or building AI weather prediction models - whether benchmarking, fine-tuning, or extending them.
• Applying generative AI and diffusion models to weather and climate is a strong plus.
• Publications in leading atmospheric, oceanic, or climate science venues and/or major ML/AI conferences.

Responsibilities

• Run numerical weather prediction models to generate high-resolution forecasts and training data.
• Inform the development of AI weather forecasting models and innovate on existing architectures.
• Evaluate pre-trained global and regional models against reanalysis, satellite, and ground observations to identify areas for improvement.
• Procure, process, and create ML-ready global and regional weather datasets, with explicit focus on data-sparse regions.
• Drive the development of next-generation multiscale, regional, and global weather forecasting systems, and their benchmarking against reanalysis and observations, especially during extreme events and over data-sparse regions.
• Tailor weather prediction models to sector-specific needs: energy (solar and wind demand/generation, grid stress), agriculture (seasonal outlooks, crop-relevant variables), and extreme-weather resilience (heatwaves, heavy precipitation, tropical and extratropical cyclones, convective storms).
• Assess the applicability of state-of-the-art AI methodologies including foundation models, generative architectures, and physics-informed ML to weather and climate forecasting.
• Work at the intersection of physics-based modeling and machine learning: hybrid physics–ML approaches, learned parameterizations, and emulators.

Benefits

• Ownership of weather forecasting models deployed for real-time applications.
• Experience working on hard, open-ended problems at the intersection of AI and physical infrastructure.
• Ability to shape technical direction and shape the frontier of AI-weather prediction revolution.
• Close collaboration with a deeply technical founding team.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior