Welcome to Planet. We believe in using space to help life on Earth.

Planet designs, builds, and operates the largest constellation of imaging satellites in history. This constellation delivers an unprecedented dataset of empirical information via a revolutionary cloud-based platform to authoritative figures in commercial, environmental, and humanitarian sectors. We are both a space company and data company all rolled into one.

Customers and users across the globe use Planet's data to develop new technologies, drive revenue, power research, and solve our world’s toughest obstacles.

As we control every component of hardware design, manufacturing, data processing, and software engineering, our office is a truly inspiring mix of experts from a variety of domains.

We have a people-centric approach toward culture and community and we strive to iterate in a way that puts our team members first and prepares our company for growth. Join Planet and be a part of our mission to change the way people see the world.

Planet is a global company with employees working remotely world wide and joining us from offices in San Francisco, Washington DC, Germany, Austria, Slovenia, and The Netherlands.

About the Role

We are seeking a highly motivated Visiting Scientist (Postdoctoral Researcher) to join our AI Research (AIR) team for a one-year residency. In this role, you will work directly with Dr. Mirela Tulbure during her sabbatical at Planet to develop our proprietary geospatial foundation models (GFMs).

While Planet has historically leveraged external models, we are now focused on building in-house models specifically trained on our unique imagery. As a postdoctoral researcher, you will be the primary technical engine behind creating temporally dense embeddings that capture the dynamic and ephemeral nature of our planet—such as rapid flooding and disaster impacts. You will collaborate with "Planeteers" across data pipelines and analytics to bridge the gap between academic research and operational AI/ML solutions.

Impact You’ll Own:

• GFM Implementation: Contribute to the design and training of a foundation model specifically optimized for Planet imagery, focusing on the integration of time-series data.
• Technical Benchmarking: Execute the systematic evaluation of existing GFM architectures (e.g., TerraMind, Prithvi, Clay) against PlanetScope data to identify performance bottlenecks and transferability.
• Prototype Development: Build and test workflows for detecting short-lived events, such as floods and fires, using high-cadence embeddings.
• Multi-Sensor Data Fusion: Develop methods to integrate PlanetScope with Sentinel-1 SAR and other commercial datasets to maintain time-series continuity under cloud cover.
• Research to Production: Work closely with Planet’s research scientists to transition experimental prototypes into scalable, operational products.
• Scholarly Contribution: Co-author findings for publication in top-tier journals and present research at leading conferences like IGARSS or CVPR.

What You Bring:

• Academic Foundation: A recently completed PhD in Geospatial Analytics, Computer Science, Remote Sensing, or a related field.
• Research Track Record: Demonstrated experience in building AI-based models for environmental change or satellite image analysis.
• AI/ML Fluency: Hands-on experience with foundation models, contrastive learning, and deep learning frameworks (PyTorch/TensorFlow).
• Advanced Technical Stack: Expert-level Python skills and proficiency with the geospatial scientific stack (e.g., xarray, Dask, Rasterio, GeoPandas).
• Data Engineering Aptitude: Experience building automated pipelines for preprocessing and labeling planetary-scale datasets.
• Collaborative Research: Experience working within a research lab environment and a strong desire to apply academic rigor to industry challenges.

What Makes You Stand Out:

• Specialized Domain Knowledge: Prior research in flood-extent mapping, water dynamics, or disaster response.
• GFM Fine-Tuning: Direct experience fine-tuning or modifying specific GFM architectures like TerraMind, Prithvi, or Clay.
• Multi-Sensor Expertise: Proven ability to work with a variety of sensors including PlanetScope, Landsat, and Sentinel-1/2.

Operational Mindset: A history of developing "human-in-the-loop" workflows or active learning strategies for labeling time-sensitive data.

Application Deadline: