📍 Location: Berlin / Remote (Germany) | ⏳ Full-time

⸻

At muffintech, we are pioneering the transformation of the insurance industry through AI-native platforms and modular agent-based systems. As we continue to expand our infrastructure and deploy more scalable AI solutions, we are looking for a DevOps-oriented AI Systems Engineer to lead the design and deployment of robust AI service architectures. You will play a central role in enabling highly available, secure, and efficient operations for multi-agent LLM systems in production.

⸻

As an AI Systems Engineer focused on DevOps and AI service architectures, you will be instrumental in designing and operationalizing the infrastructure that powers our intelligent systems. Your responsibilities will span the implementation of AI-driven workflows and multi-agent automations, collaboration on service-oriented system architectures, and the deployment of robust, secure pipelines and networked environments in the cloud. You’ll ensure that our AI applications operate reliably and efficiently at scale, enabling seamless integration across our ecosystem of tools and services.

⸻

• Design, implement, and maintain scalable AI infrastructure on Microsoft Azure.
• Build and manage Kubernetes-based deployment pipelines for LLM agent systems.
• Automate provisioning, monitoring, and scaling of compute resources for training and inference.

• Architect and operationalize modular microservices and APIs for AI workflows.
• Ensure system observability, performance monitoring, and auto-healing mechanisms.
• Implement secure and compliant CI/CD workflows for production-ready AI services.

• Integrate AI services with internal platforms (CRMs, databases, user-facing systems).
• Collaborate on orchestration of multi-agent systems with dynamic task coordination.
• Optimize latency, throughput, and resilience in cloud-native environments.

• Work closely with Product, and diverse Engineering teams to translate prototypes into scalable systems.
• Contribute to internal tooling for model evaluation, workflow debugging, and reliability testing.
• Shape muffintech’s standards for AI system deployment, monitoring, and lifecycle management.

⸻

• Proven experience with Microsoft Azure, including services for compute, networking, and storage.
• Deep knowledge of Kubernetes (AKS or general), Helm charts, and containerized applications.
• Proficiency with infrastructure-as-code tools (Terraform, Pulumi) and CI/CD systems (GitHub Actions, Azure DevOps).
• Background in Machine Learning, NLP, or AI systems engineering.

• Strategic thinker with a pragmatic approach to operational scalability.
• Comfortable working across disciplines to bring engineering rigor to experimental systems.
• Excellent communication and documentation skills, with an ability to make complex infrastructure decisions accessible to diverse stakeholders.

• Be part of a mission-driven team reshaping AI deployment in the insurance space.
• Build resilient systems that support cutting-edge multi-agent AI workflows.
• Enjoy a flexible, collaborative, and remote-friendly work culture.
• Opportunity to shape the DevOps and architectural backbone of a modular AI platform.