{
  "id": "responsibility:inference-latency-sla",
  "_kind": "Responsibility",
  "_file": "role/responsibilities/responsibilities-expanded-2.yaml",
  "_cluster": "role",
  "attributes": {
    "displayName": "Inference latency SLA",
    "cadence": "continuous",
    "description": "Ensure ML model inference meets latency targets — monitor P50/P99\nresponse times, optimize serving infrastructure, and enforce\nperformance budgets for model endpoints.\n"
  },
  "outgoingEdges": [
    {
      "from": "responsibility:inference-latency-sla",
      "to": "role:ml-engineer",
      "kind": "held_by",
      "attributes": {}
    },
    {
      "from": "responsibility:inference-latency-sla",
      "to": "role:machine-learning-ops-engineer",
      "kind": "held_by",
      "attributes": {}
    },
    {
      "from": "responsibility:inference-latency-sla",
      "to": "skill-area:model-serving",
      "kind": "requires_expertise",
      "attributes": {}
    },
    {
      "from": "responsibility:inference-latency-sla",
      "to": "skill-area:inference-optimization",
      "kind": "requires_expertise",
      "attributes": {}
    }
  ],
  "incomingEdges": [
    {
      "from": "role:machine-learning-ops-engineer",
      "to": "responsibility:inference-latency-sla",
      "kind": "holds_responsibility"
    },
    {
      "from": "role:speech-engineer",
      "to": "responsibility:inference-latency-sla",
      "kind": "holds_responsibility"
    }
  ]
}