MLOps Engineer (m/w/d)

Job summary

Rheinmetall is seeking an MLOps Engineer to deploy and operate Machine Learning models in standardized and scalable production environments. The role involves implementing robust traffic-handling and autoscaling mechanisms, managing advanced deployment strategies, and optimizing inference performance. The engineer will also be responsible for packaging and releasing models in containerized environments and establishing comprehensive monitoring.

Qualifications

• Successfully completed degree in Computer Science, Machine Learning, Artificial Intelligence, Software Engineering, or a comparable qualification.
• Professional experience in Machine Learning Operations (MLOps), Platform Engineering, or DevOps environments supporting Machine Learning systems.
• Profound experience in deploying and operating Machine Learning models in production environments.
• Solid knowledge of containerized workloads and orchestration platforms for scalable model deployment.
• Experience working with model versioning systems and managing Machine Learning artifacts across different environments.
• Proficient in written and spoken English.
• Practical experience in optimizing Machine Learning models for efficient inference and hardware utilization.
• Structured and analytical approach to solving complex operational challenges in Machine Learning systems.
• Strong collaboration and communication skills for working with engineering, data science, and platform teams.

Responsibilities

• Deploy and operate Machine Learning models in standardized and scalable production environments.
• Implement robust traffic-handling and autoscaling mechanisms for reliable and efficient model serving.
• Design and manage advanced deployment strategies to minimize risk during model releases and updates.
• Optimize inference performance through improved hardware utilization and latency reduction for production workloads.
• Package and release Machine Learning models in fully containerized and version-controlled environments.
• Ensure reproducibility and integrity of model artifacts across development, test, and production systems.
• Establish comprehensive monitoring for inference performance, data quality, and model behavior in production.
• Support governance and compliance by maintaining traceable release artifacts, validation results, and audit-proof documentation.

Skills

Languages

Relocation