At Kilimo we are looking for an experienced Senior Machine Learning Engineer & DevOps Specialist with a solid background in deploying and scaling machine learning models and managing DevOps processes. The ideal candidate will have a proven track record in building and maintaining ML pipelines and expertise in DevOps practices to ensure seamless integration, deployment, and scalability of machine learning solutions. Extensive knowledge of modern machine learning frameworks and strong DevOps skills, particularly within climate and agricultural domains, are essential. Key Responsibilities Model Development and Deployment Design, build, and optimize scalable machine learning models for climate and agricultural applications. Implement production-ready ML pipelines, encompassing feature engineering, model training, and evaluation. Deploy and monitor models in production environments to ensure performance, reliability, and scalability.Design, build, and optimize scalable machine learning models for climate and agricultural applications. Implement production-ready ML pipelines, encompassing feature engineering, model training, and evaluation. Deploy and monitor models in production environments to ensure performance, reliability, and scalability. Create and maintain databases through data lakes for efficient data storage and access. Utilize and generate ETLs to extract, transform, and load data, ensuring compatibility and accessibility throughout the ML pipeline. MLOps and DevOps Integration Develop and maintain automated systems for model retraining, versioning, and monitoring using MLOps best practices. Design and implement CI/CD pipelines tailored for machine learning workflows to streamline development and deployment processes. Manage infrastructure as code (IaC) using tools like Terraform or Ansible to provision and maintain cloud resources. Ensure robust monitoring, logging, and alerting systems are in place for both ML models and underlying infrastructure. Infrastructure Management Oversee the deployment and orchestration of containerized applications using Docker and Kubernetes. Optimize cloud infrastructure (AWS, Azure, GCP) for cost, performance, and scalability to support ML workloads. Collaborate with DevOps teams to enhance system reliability, security, and efficiency. Domain-Specific Applications Apply machine learning techniques to analyze climate, weather, and agricultural data. Develop predictive models for crop growth, irrigation optimization, and environmental sustainability. Utilize remote sensing data and satellite imagery for geospatial analysis and decision-making. Research and Optimization Stay updated on the latest trends in machine learning and DevOps, applying state-of-the-art techniques to projects. Optimize models and infrastructure for performance, scalability, and accuracy in large-scale deployments. Conduct experiments to test and validate hypotheses for ML-driven and DevOps-enhanced solutions.