AI Platform Engineer (m/f/x) at Scalable GmbH
Germany
Posted
on-site · full-time · Visa sponsorship
Apply for this role at Scalable GmbH
Responsibilities:
- Design, build and operate an internal AI provisioning platform to provide secure, cost-aware access to LLMs and MCP servers (e.g., LiteLLM integrations).
- Implement observability for model requests and responses: structured logging, metrics, traces, dashboards and alerts (Datadog, Langfuse or equivalent).
- Enforce model governance: authentication, RBAC, data privacy controls, rate limiting and API cost tracking/reporting.
- Collaborate with AI Software Engineers to integrate agentic workflows and cloud-native architectures into production systems.
- Build infrastructure for reliability: CI/CD for models and infra, automated testing, canary/deployment strategies, runbooks and SLO monitoring.
- Optimize cost and performance across model endpoints and APIs, including batching, caching and autoscaling strategies.
Requirements:
- Bachelor’s or Master’s in CS, Software Engineering or related field.
- Several years in Platform Engineering/DevOps/SRE or backend engineering supporting production systems.
- Strong cloud experience (AWS preferred) and Infrastructure-as-Code (Terraform) expertise.
- Proficiency in at least one language (Python or Go) and experience with containers and CI/CD pipelines (Docker, GitHub Actions/CI).
- Experience with observability and telemetry tooling (Datadog, tracing, logging) and familiarity with model observability concepts.
- Understanding of API governance, security best practices, cost management and production deployment patterns.