Senior Site Reliability Engineer
- Location
- Reading, England, United Kingdom
Triton, vLLM, or similar) with real latency and cost constraints(preferred RayServe) MLOps pipeline tooling - training pipelines, model registries, feature stores, and lineage (Kubeflow, MLflow, Feast, Weights & Biases, or equivalents) LLMOps in production - inference serving, prompt/version management, and LLM observability (tracing, evals, drift, guardrails, cost per request) Governing ...