GHGSat is mapping and tracking the world's greenhouse gas (GHG) emitters. To achieve this goal, GHGSat operates its own satellite and aircraft sensors to collect emissions data and uses these with third-party data to inform an analytics pipeline that:
Detects and quantifies GHG emissions
Identifies and classifies potential GHG emitters
Generates valuable insights for our customers
We're looking for a
Geospatial Data Engineer
based in London, UK, who will play a key role in building and optimising our geospatial data and AI/ML pipelines to support GHGSat’s mission of driving climate impact. This role involves integrating geospatial data from various sources, designing robust data systems, and contributing to analysis and insights generation. Data Pipeline Development Design, implement, and optimise scalable geospatial data and AI/ML pipelines. Integrate new data sources, including satellite and terrestrial, both public and proprietary. Re-engineer and validate existing pipelines, ensuring high-quality and performance standards. Geospatial Data Management Blend and process various geospatial data sources to create artifacts for exploratory analysis and insights. Build scripts and automations for geospatial data processing, using tools like QGIS, GeoPandas, Rasterio, Xarray, and rioxarray. Conduct geospatial analysis and contribute to mapping and visualization. Automation and Deployment Contribute to the automation of testing, deployment, and monitoring of data pipelines and AI/ML models using Airflow, Docker, and AWS services. Collaboration and Innovation Work collaboratively with the Analytics team, Subject Matter Experts, and cross-teams to prototype new data solutions. Explore applications of AI/ML for geospatial data and integrate emerging technologies where possible. Present findings and recommendations to both technical and non-technical stakeholders, fostering a data-driven culture. Communicate complex geospatial data insights in a clear, accessible manner to support informed outcomes. Desired Attributes Impact-Driven Mindset: Passionate about contributing to environmental sustainability and climate impact. Self-motivated and collaborative worker: Able to work proactively and as part of a team, using initiative to uncover solutions to improve workflows and data processes. Continuous Learner: Continuously seeks out new geospatial technologies, trends, datasets, and tools to incorporate into projects. Effective Communicator: Able to convey technical information effectively to both technical and non-technical audiences, promoting a collaborative environment. Qualifications 3+ years of experience in data engineering, with specific expertise in geospatial data processing and analysis. Proficiency in Python and experience with libraries like Pandas, NumPy, SciPy, and scikit-image. Experience with geospatial libraries such as GeoPandas, Rasterio, Xarray, rioxarray, and QGIS. Familiarity with SQL and geospatial databases (e.g., PostgreSQL/PostGIS). Comfortable with cloud infrastructure (AWS preferred), containerization tools (Docker), and version control (Git). Knowledge of AI/ML concepts applied to geospatial data is a plus. Knowledge of frameworks like ClearML and STAC is beneficial. We understand that you may not have experience with every tool or technique listed here.
If you have a strong foundation in geospatial data engineering and a willingness to learn, we encourage you to apply! Competitive salary + stock options for all full-time employees Full comprehensive benefits Statutory leave + paid time off Flexible hybrid work environment
#J-18808-Ljbffr
Geospatial Data Engineer
based in London, UK, who will play a key role in building and optimising our geospatial data and AI/ML pipelines to support GHGSat’s mission of driving climate impact. This role involves integrating geospatial data from various sources, designing robust data systems, and contributing to analysis and insights generation. Data Pipeline Development Design, implement, and optimise scalable geospatial data and AI/ML pipelines. Integrate new data sources, including satellite and terrestrial, both public and proprietary. Re-engineer and validate existing pipelines, ensuring high-quality and performance standards. Geospatial Data Management Blend and process various geospatial data sources to create artifacts for exploratory analysis and insights. Build scripts and automations for geospatial data processing, using tools like QGIS, GeoPandas, Rasterio, Xarray, and rioxarray. Conduct geospatial analysis and contribute to mapping and visualization. Automation and Deployment Contribute to the automation of testing, deployment, and monitoring of data pipelines and AI/ML models using Airflow, Docker, and AWS services. Collaboration and Innovation Work collaboratively with the Analytics team, Subject Matter Experts, and cross-teams to prototype new data solutions. Explore applications of AI/ML for geospatial data and integrate emerging technologies where possible. Present findings and recommendations to both technical and non-technical stakeholders, fostering a data-driven culture. Communicate complex geospatial data insights in a clear, accessible manner to support informed outcomes. Desired Attributes Impact-Driven Mindset: Passionate about contributing to environmental sustainability and climate impact. Self-motivated and collaborative worker: Able to work proactively and as part of a team, using initiative to uncover solutions to improve workflows and data processes. Continuous Learner: Continuously seeks out new geospatial technologies, trends, datasets, and tools to incorporate into projects. Effective Communicator: Able to convey technical information effectively to both technical and non-technical audiences, promoting a collaborative environment. Qualifications 3+ years of experience in data engineering, with specific expertise in geospatial data processing and analysis. Proficiency in Python and experience with libraries like Pandas, NumPy, SciPy, and scikit-image. Experience with geospatial libraries such as GeoPandas, Rasterio, Xarray, rioxarray, and QGIS. Familiarity with SQL and geospatial databases (e.g., PostgreSQL/PostGIS). Comfortable with cloud infrastructure (AWS preferred), containerization tools (Docker), and version control (Git). Knowledge of AI/ML concepts applied to geospatial data is a plus. Knowledge of frameworks like ClearML and STAC is beneficial. We understand that you may not have experience with every tool or technique listed here.
If you have a strong foundation in geospatial data engineering and a willingness to learn, we encourage you to apply! Competitive salary + stock options for all full-time employees Full comprehensive benefits Statutory leave + paid time off Flexible hybrid work environment
#J-18808-Ljbffr
