About this role
Join Cisco's AI Platform and Services team to build and operate the core infrastructure powering AI across Splunk and Cisco. You will ensure mission-critical AI workloads like LLM inference and VectorDB/RAG are highly available, scalable, secure, and cost-efficient in production across hybrid multi-cloud environments.
What we are looking for 6
- Operate and optimize multi-tenant LLM inference, VectorDB/RAG, and MCP platforms
- Drive platform resiliency with SLOs, SLIs, and automated health checks
- Automate operations for seamless rollouts, autoscaling, and self-healing
- Optimize GPU and inference performance using Kubernetes and vLLM
- Lead production incident response and conduct root-cause analyses
- Partner with AI researchers and product developers on production readiness