AI Platform Engineer (m/f/x) at Scalable GmbH
München, Germany, Germany
Posted
on-site · full-time · Visa sponsorship
Apply for this role at Scalable GmbH
Responsibilities:
- Build and operate an internal AI provisioning platform to provide secure, consistent access to LLMs and MCP servers (e.g., via LiteLLM).
- Implement end-to-end observability for model usage and performance (logging, metrics, tracing, alerts) using tools like Datadog and Langfuse.
- Enforce model governance: security controls, data privacy safeguards, rate limiting and API cost management.
- Design, deploy and maintain cloud-native infrastructure using AWS and Infrastructure as Code (Terraform).
- Collaborate with AI software engineers to integrate agentic workflows and ensure production reliability and cost-efficiency.
Requirements:
- Several years of experience in Platform Engineering, DevOps, SRE or backend engineering.
- Strong AWS experience and proven expertise with Terraform or similar IaC tools.
- Proficiency in at least one language such as Python or Go; experience building CI/CD pipelines and containerized deployments (Docker).
- Familiarity with observability and APM tools (Datadog, Langfuse) and monitoring production ML/LLM systems.
- Knowledge of model governance, API cost controls, security best practices and production reliability principles.