About X, the Moonshot Factory
X is a diverse group of inventors and entrepreneurs who build and launch technologies that aim to improve the lives of millions, even billions, of people. Our goal: 10x impact on the world’s most intractable problems, not just 10% improvement. We approach projects that have the aspiration and riskiness of research with the speed and ambition of a startup.
About the Team:
Our team – Bellwether – operates at the intersection of machine learning, geospatial data, and pressing issues with enterprise customers, governments, and more. We focus on severe weather manifestations of climate change, such as wildfires, and aim to use a wide range of data and analytics to better understand and predict what these events could mean for communities and businesses across the globe. We do this through the detection and classification of the features and patterns of the natural and built worlds, the application of cutting-edge machine learning, and the redesign of the full geo-ML workflow. This work extends into development and production-level work as well, as Bellwether also has a number of products that are live with customers. The result: tools and models that allow a range of industries to better leverage earth observation insights.
About the Role:
We are looking for a Lead Data Scientist to build and unify the data infrastructure that powers our model training pipelines for Project Bellwether. In this role, you will lead the effort to construct a comprehensive multimodal data corpus—integrating geospatial, imagery, sensor, and operational feeds—that serves as a strategic moat for pre- and post-disaster response and resilience.
Your primary focus will be designing automated ingestion pipelines for complex multimodal datasets, establishing rigorous data quality validation frameworks, and managing dataset versioning to support continuous machine learning training loops. You will bridge the gap between operations, remote annotation teams, and machine learning engineers to ensure our disaster-response models are trained on reliable, high-fidelity, and well-structured data.
How you will have 10X impact:
- Architect and build automated ETL (Extract, Transform, Load) and ELT (Extract, Load, Transform) data pipelines to aggregate, clean, and harmonize data from disparate sources, databases, and operational ingestion flows.
- Implement DataOps practices, including data quality monitoring, automated schema validation, and anomaly detection to catch corrupt or mislabeled data early.
- Standardize and integrate third-party annotation workflows and remote labeling feeds into unified datasets ready for model training.
- Design and maintain dataset versioning and storage systems to allow reproducible machine learning experiments and seamless data retrieval.
- Partner with ML engineers and operations teams to turn geospatial, imagery, and sensor metadata into structured training features.
- Lead the end-to-end development of multimodal machine learning models, driving innovation from research and dataset architecture to production deployment for pre- and post-disaster response.
- Define product and data strategy around the multimodal data corpus, leveraging proprietary datasets as a strategic moat for AI-driven disaster resilience tools.
- Collaborate with engineering teams to optimize model performance, scalability, and integration into existing product workflows.
- Establish best practices for MLOps, including model versioning, automated testing, and performance tracking to ensure reliable and high-quality deployments.
- Help hire and grow the data science function, setting the technical bar and culture as the team scales.
- Design, build, and maintain robust data ontologies and taxonomies to systematically organize, categorize, and integrate complex geospatial and multimodal datasets.
What you should have:
- Education: Advanced Degree in Computer Science, Data Engineering, Software Engineering, or a related technical field.
- Data Engineering & Architecture: 7+ years experience building scalable data pipelines, managing relational and non-relational databases, and unifying fragmented data storage systems.
- Modern Python Proficiency: Expertise in Python and data manipulation libraries (e.g., Pandas, NumPy, or SQL).
- Data Quality & DataOps: Practical experience implementing automated data validation, quality control frameworks, and dataset versioning practices.
- ML Data Lifecycle Understanding: Hands-on experience structuring datasets specifically for machine learning workflows, including handling annotations, metadata tracking, and training set curation.
It’d be great if you also had these:
- Pipeline Design & Ingestion: Construct automated ELT/ETL pipelines to aggregate, clean, and integrate complex geospatial, satellite image, and telemetry streams into unified repositories at scale and large volume.
- Quality Governance & DataOps: Deploy comprehensive data validation systems, schema checks, and anomaly monitoring to ensure machine learning components rely on robust, high-fidelity information.
- Versioning & Tracking: Maintain structured dataset versioning infrastructure to enable reproducible model testing and efficient retrieval of operational features.
- Workflow & Label Integration: Harmonize external labeling pipelines and annotation feeds into streamlined, model-ready training assets.
- Cross-Functional Strategy: Partner with software engineers, data scientists, and operational stakeholders to convert complex sensor attributes into targeted features for prediction pipelines.
- Geospatial Data: Experience working with geospatial data (good knowledge of data sources and formats), GIS tools, and spatial analytics libraries (e.g., GDAL, GeoPandas, Rasterio, Shapely, Zarr, COGs…).
The US base salary range for this full-time position is $207,000 - $311,000 + bonus + benefits. Our salary ranges are determined by role, level, and location. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training. Your recruiter can share more about the specific salary range for your location during the hiring process.
Please note that the compensation details listed in US role postings reflect the base salary only, and do not include bonus, or benefits.