LLM Ops Engineer

Build model evaluation tooling for clinical accuracy latency cost and safety; Build prompt engineering and model data pipelines; Collaborate on fine tuning workflows model selection prompt versioning and context management; Define alerting thresholds and build model health monitoring tooling; Design deploy maintain AWS EKS infrastructure for GPU model workloads; Design offline evaluation harnesses automated regression tests and dashboards; Instrument token usage latency P99 GPU memory pressure h