Lead Geo-Spatial AI Engineer

Role Overview

We are seeking a high-energy, curious, and versatile Lead Geospatial AI Engineer to head our

GeoAI R&D team. In this role, you will be the technical architect behind our most complex

computer vision problems and the operational lead driving multiple projects to success. You

must be comfortable pivoting between deep research, hands-on coding, and strategic team

management in a fast-paced, agile environment.

Key Responsibilities

Team Leadership & Mentorship: Lead a cross-functional team of AI engineers; foster a

culture of curiosity, continuous learning, and rapid experimentation.

Agile Project Execution: Oversee the end-to-end lifecycle of multiple R&D projects, ensuring

timely delivery of prototypes and production-ready models.

Advanced R&D: Research and implement state-of-the-art (SOTA) computer vision

architectures (e.g., Vision Transformers, Diffusion Models, Segment Anything) for diverse

geospatial analytics.

Scalable AI Pipelines: Design robust MLOps workflows to handle massive multi-modal

datasets (Satellite, SAR, LiDAR, Aerial) from ingestion to deployment.

Cross-Functional Collaboration: Partner with product and business leads to translate

abstract research into actionable industry solutions for sectors like [Climate

Tech/Defense/Urban Planning].

Technical Stack Requirements

Core AI & Computer Vision:

Frameworks: Mastery of PyTorch (preferred) or TensorFlow.

CV Libraries: Expert use of OpenCV, TorchVision, SAMGeo, Detectron2, and YOLO variants.

Advanced Modeling: Experience with Hugging Face Transformers for Vision and Segment

Anything (SAM).

Geospatial Engineering Stack:

Processing: Expert proficiency with GDAL/OGR, Rasterio, and GeoPandas.

Geometry: Deep knowledge of Shapely and Pyproj for CRS management.

Analysis: Experience with Google Earth Engine, TorchGeo, and QGIS/ArcGIS Pro.

Data & MLOps Infrastructure:

Cloud Platforms: Extensive experience with AWS (SageMaker), Google Cloud (Vertex AI), or

Azure ML.

Pipelines & Versioning: Proficiency in MLflow, DVC (Data Version Control), and Kubeflow.

Annotation: Familiarity with high-volume labeling tools like CVAT, Labelbox, or Roboflow.

Deployment: Containerization via Docker and orchestration with Kubernetes.

Soft Skills & Mindset

Problem-Solving Curiosity: A figure it out attitude when faced with messy, unstructured, or

sparse geospatial data.

Radical Flexibility: Ability to shift priorities across projects without sacrificing quality or team

morale.

Action-Oriented Leadership: High bias for action; you prefer a working prototype over a

perfect theoretical model.

Education & Experience

Education: BT/MS/PhD in Computer Science, Geoinformatics, or a related quantitative field.

Experience: 7+ years in AI/CV, including 2+ years leading technical teams and managing

multi-project portfolios.