Senior Production Engineer, Managed AI

About the role

Senior role keeping a cloud platform for large AI workloads reliable and scalable: operating managed LLM serving, building reliability tooling, and defining SLIs/SLOs. It involves observability, performance tuning, and troubleshooting distributed AI systems. Candidates need production software skills, distributed systems experience, hands-on LLM or AI infrastructure work, and an SRE mindset.