This job offer is no longer available
About
Keeps the AI platform running, scalable, secure, and observable in production. This person owns production deployment and ensures enterprise clients get bank-grade reliability.
Essential Skills (Dealbreakers) • Azure infrastructure:
Container Apps, API Management, Virtual Networks, Key Vault, Log Analytics. Must build and maintain production cloud infrastructure for AI workloads. • CI/CD for AI systems:
Azure DevOps pipelines that include eval runs as quality gates - not just build/deploy, but automated evaluation checkpoints before production promotion. • LLM operations:
Model routing, proxy management, token economics, cost optimization at scale. Understands the difference between monitoring a traditional API and monitoring an AI system. • Enterprise security:
Zero Trust networking, secrets management, compliance infrastructure (ISO 42001, EU AI Act). Bank-grade security posture is non-negotiable.
Desired Skills (Nice-to-Have) • LiteLLM proxy configuration • Langfuse observability setup (tracing, cost tracking, latency monitoring) • Experience supporting compliance certifications
Red Flags ✗ Only traditional infrastructure with no understanding of LLM-specific operations (token costs, model versioning, prompt-driven deployments) ✗ Cannot articulate difference between monitoring a traditional API vs. an AI system ✗ No enterprise security experience
Languages
- English
Notice for Users
This job was posted by one of our partners. You can view the original job source here.