#### About Us
SkyServe is sensor agnostic "Insights-as-a-Service" edge computing platform on-board satellites, providing inferences to industries, system integrator, and geospatial developers.
#### Position 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.
Deep-tech Work India