Specific ResponsibilitiesUnder the overall guidance of the DRM Program Head, the DevOps & Machine Learning Expert will undertake the following tasks:
Specific Responsibilities
Ensure hydrological forecasting chains in use at ICPAC run operationally in an automated forecast cycle, with new product releases deployed without interruption to service.
Ensure harmonized regional hydrological reference and observation datasets are maintained, with documented quality control and exchange interfaces for national hydrological services.
Maintain an operational STAC API and analysis infrastructure for hazard, exposure, and impact data, with reliable processing pipelines across all integrated models.
Support the operationalization of East Africa Flood Watch at functional parity with Drought Watch, ensuring warnings and products are integrated into the East Africa Hazard Watch Portal.
Develop and maintain automated data processing and reporting workflows, including impact-based forecast bulletin generation with language-model-assisted drafting under documented evaluation and guardrails.
Provide technical support to Member States, National Meteorological and Hydrological Services (NMHSs), and regional partners on IGAD flood-monitoring activities, ensuring requests are addressed effectively.
Support implementation of calibrated post-processing and multi-model ensemble combination in operations, supported by documented methodology.
Deploy and maintain Bayesian Network risk models and inference services integrated with risk-monitoring applications.
Contribute event-based climate storylines to drought and flood event catalogues.
Develop and maintain forecast verification frameworks with routine skill reporting and documented governance for all operational models.
Implement reproducible multi-cloud infrastructure as code with ecFlow and Prefect scheduling, CI/CD and GitOps delivery, production observability, and tested disaster-recovery procedures.
Prepare and maintain complete technical documentation, deployment guides, JupyterHub tutorials, training materials, and stakeholder handover documentation.
Perform such other duties as may be assigned from time to time.Key Educational Qualifications and Professional ExperienceAcademic Qualification
Key Educational Qualifications and Professional Experience
Academic Qualification
University degree in Computer Science, Geo-Informatics, Hydroinformatics, Computer Engineering, Data Science, Software Engineering, Information Technology, or another relevant field. An advanced degree is an added advantage.
Candidates should demonstrate qualifications and proficiency in web application development and geo-application development by providing links to at least two samples of previous work and/or GitHub code.Professional Work Experience
Professional Work Experience
Minimum of four (4) years of relevant experience in geo-application design and development.
Proven proficiency in web application development and geo-application development, demonstrated through a portfolio of developed products, including at least two samples of previous work and/or GitHub repositories.
Demonstrated experience operating production cloud infrastructure under daily operational deadlines and (adsbygoogle=window.adsbygoogle||[]).push({});deploying machine learning models in operational environments rather than research settings.
Experience supporting national institutions within operational early warning systems is desirable.
Strong experience in scripting and automation of geoprocessing and large-scale data workflows, particularly using Python, with sound knowledge of SQL and PostGIS.
Experience with web technologies including HTML, CSS, and JavaScript, and development of production-ready geospatial web applications using Node.js, React, Mapbox GL, Leaflet, GeoServer, MapServer, and GDAL.
Experience developing REST APIs and working with microservices architecture. Knowledge of Go programming language is an added advantage.
Strong understanding of OGC geospatial standards including WMS, WFS, WCS, WPS, and Simple Features for SQL.
Experience handling and analyzing Earth Observation data in multiple formats.
Experience with STAC API and PySTAC, workflow orchestration using ecFlow and Prefect, and scientific computing tools such as xarray, dask, and the NumPy ecosystem.
Experience using rasterio, geopandas, GRIB2, Zarr, Cloud Optimized GeoTIFFs (COG), VirtualiZarr, Icechunk, and kerchunk.
Strong experience with PostgreSQL/PostGIS and TimescaleDB.
Hydroinformatics expertise including operationalization of rainfall-runoff models, hydrodynamic models, rapid inundation forecasting systems, forcing preparation, catchment and river network management, terrain data handling, hydrometric and remotely sensed observations, and hydrological data standards.
Experience with container orchestration technologies including Docker, Kubernetes, and Helm.
Experience implementing GitOps workflows using ArgoCD.
Experience with multi-cloud environments including Google Cloud Platform (GCP) and Amazon Web Services (AWS), utilizing Terraform, Coiled, and CI/CD pipelines.
Knowledge of CUDA and GPU environment management.
Experience in observability, incident response, cloud security, and cloud cost management.
Knowledge of impact-based forecasting systems and climate modelling workflows.
Experience in ensemble post-processing, calibration, downscaling, Bayesian networks, forecast verification, MLOps practices, and Large Language Model (LLM) integration, evaluation, and guardrail implementation.