All jobs
Staff Site Reliability Engineer — AI Platform
Amsterdam · HybridSenior (5–10 years)Full-timePosted 6 Aug 2026
About the job
What you'll do
You will own the reliability, performance, and cost optimization of the AI infrastructure, including inference services and LLM integrations. Additionally, you will design the AI Gateway, establish observability standards, and scale AI expertise across the engineering organization.
What they're looking for
The role requires 5+ years of experience in SRE or infrastructure engineering with hands-on production experience in LLM-backed systems. Candidates must possess deep cloud-native skills, strong observability practices, and the ability to drive technical direction at a staff level.
Full description