Role Description This is a remote position with occasional travel. As our first engineering hire, you will own the geospatial processing layer and the user-facing product end-to-end. That means: - Building and operating the cloud pipelines that transform raw imagery into agency-ready outputs. - Building the interface that puts those outputs in front of operators and dispatchers during active incidents. - Transitioning into leadership as the team grows. Qualifications - Hands-on experience building cloud processing workflows (GCP, Azure, AWS, etc.) using open geospatial libraries (GDAL, PROJ, Rasterio, GeoPandas, or similar). - 3+ years’ experience building production web applications with a modern JS stack (React, Vue, or equivalent). - Familiarity with GIS platforms — ESRI products, open-source equivalents, and cloud. - Experience working with raster imagery data — tiling, reprojection, COG generation, and serving processed imagery to map-based UIs. - Experience building map-centric UIs — rendering geospatial data, vector overlays, and imagery in a browser using Mapbox GL JS, Leaflet, Cesium, or similar. - Working knowledge of photogrammetry concepts — orthorectification, georeferencing, and aerial image processing workflows. Requirements - Experience with map rendering libraries (Mapbox, Leaflet, Cesium, etc.). - Background in fire, emergency management, aviation, or public safety domains. - Hands-on experience with photogrammetry pipelines and tools (OpenDroneMap, Pix4D, Agisoft Metashape, or similar). - Familiarity with agency GIS platforms and field situational awareness tools. - Experience with satellite or aerial imagery processing and raster data visualization. - Preference for west coast location. Extra points for PNW. A Note on the Role We are a small, early-stage team. This role will require comfort with ambiguity, ownership beyond a narrow job description, and direct engagement with end users in operational environments.

• Build Scalable ML Systems: Design and build the end-to-end machine learning infrastructure, setup platform for transitioning experimental Data Science models into robust, high-availability production services. • Real-Time Inference at Scale: Build automation for deploying low-latency services to serve model inferences in milliseconds. You will power real-time decisions across the platform, from dynamic oddsmaking and risk analysis to smart deposit defaults. • Feature Engineering & Data Strategy: You will lead the creation and optimization of a centralized feature store required to train complex models across diverse business domains. • End-to-End MLOps: You will work with the Infrastructure team to build and operate core ML platform components for training and experimentation enablement considering developer experience. You will champion best practices for model deployment, monitoring, and CI/CD for ML. You will implement automated retraining pipelines and observability for ML systems to ensure data drift and model degradation are caught and addressed instantly.

• Designs and Implements complex, mission-critical transformational enterprise grade technical solutions for clients. • Develops high quality deliverables and presentations for Client engineering teams and senior leaders. • Creates and presents solution designs, options, ideas, and innovations to clients’ senior leadership teams. • Develops and Maintains Technical Roadmaps and Innovation Plans. • Develops and Implements CI/CD solutions. • Establishes project estimates and plans, identifies risks and mitigations, oversees development and delivery of technical solutions. • Mentor and support project teammates • Actively lead collaboration within our technical communities • Up to 25% travel

• Design, implement, and maintain cloud-native platform to support AI and data workloads, with a focus on AI and data platforms such as Databricks and AWS Bedrock. • Build and manage scalable data pipelines to ingest, transform, and serve data for ML and analytics. • Develop infrastructure-as-code using tools like Cloudformation, AWS CDK to ensure repeatable and secure deployments. • Collaborate with AI engineers, data engineers, and platform teams to improve the performance, reliability, and cost-efficiency of AI models in production. • Drive best practices for observability, including monitoring, alerting, and logging for AI platforms. • Contribute to the design and evolution of our AI platform to support new ML frameworks, workflows, and data types. • Stay current with new tools and technologies to recommend improvements to architecture and operations. • Integrate AI models and large language models (LLMs) into production systems to enable use cases using architectures like retrieval-augmented generation (RAG).