On-Site Senior MLOps Engineer: Real-Time LLM Infra

Nace AI in Palo Alto, CA is seeking a Senior MLOps Engineer to own the production-grade ML infrastructure that turns research into reliable systems. You will design and operate training orchestration, model registries, CI/CD for models, and automated evaluation pipelines across cloud and on-prem environments.

You'll lead LLM/SLM serving, scale low-latency inference with vLLM and related tooling, manage multi-GPU clusters, and implement observability and audit-ready controls to support enterprise