🛠 Tech Stack

💼 About This Role

You'll develop proprietary geospatial foundation models for Planet's satellite imagery during a one-year postdoctoral residency. Your core impact will be creating temporally dense embeddings to capture dynamic environmental events like flooding. This role bridges academic research and operational AI/ML at a leading space and data company.

🎯 What You'll Do

• Design and train foundation models optimized for Planet imagery with time-series data.
• Evaluate existing GFM architectures (TerraMind, Prithvi, Clay) against PlanetScope data.
• Build workflows for detecting short-lived events like floods and fires using embeddings.
• Develop methods to integrate PlanetScope with Sentinel-1 SAR for time-series continuity.

📋 Requirements

• Recently completed PhD in Geospatial Analytics, Computer Science, Remote Sensing, or related field.
• Demonstrated experience building AI-based models for environmental change or satellite image analysis.
• Hands-on experience with foundation models, contrastive learning, and deep learning frameworks (PyTorch/TensorFlow).
• Expert-level Python skills and proficiency with geospatial scientific stack (xarray, Dask, Rasterio, GeoPandas).

✨ Nice to Have

• Prior research in flood-extent mapping, water dynamics, or disaster response.
• Direct experience fine-tuning or modifying GFM architectures like TerraMind, Prithvi, or Clay.
• Proven ability to work with multiple sensors including PlanetScope, Landsat, and Sentinel-1/2.

🎁 Benefits & Perks

• 🏖️ Generous Paid Time Off in addition to holidays and company-wide days off
• 👶 16 Weeks of Paid Parental Leave
• 🏠 Home Office Reimbursement
• 📚 Tuition Reimbursement and LinkedIn Learning access
• 🏥 Comprehensive Medical, Dental, and Vision plans with HSA company contribution

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Call· 30 min
2. 2Technical Screen· 60 min
3. 3On-site Interview· Half day