The reference stack that decides whether an LLM solution survives an audit, a Black Friday, or a prompt-injection incident — the seven layers, multi-tenancy, the SLO-first design move, streaming RAG vs nightly ETL, and the architecture round interviewers actually run.

• →Enterprise AI Architecture

Evals are the only artifact that tells a customer you know what “good” means — the five-class metric taxonomy, LLM-as-judge calibration to >80% human agreement, offline gates vs online sampling, capability-vs-regression suites, and the grader-is-production-code lesson behind Anthropic’s 42%→95% jump.

• →Evaluation Design

The discipline that lets you tell a customer in a Friday-night incident review what actually happened — the LLM span schema, why time-to-first-token is the new p95 (and how Intercom cut 2s with it), feedback loops that close the system, and continuous-eval drift detection.

• →AI Observability

The substrate that connects AI to a customer’s systems — MCP’s host/client/server model and primitive vocabulary, why it reframes integration from N×M to N+M, the consent/exec security boundaries, and the gateway pattern (Runlayer’s $11M bet on 18,000+ servers) that collapses the OAuth sprawl.

• →Governed MCP Integration

The customer-facing half of the job — the SE’s discovery stack (MEDDPICC, SPIN implication questions, Challenger reframe), the fixed five-pain stack of enterprise AI, value/ROI storytelling with credible 200–600% ranges, arming the champion, and the discovery round interviewers run.

• →Discovery and Value Selling

Run the full arc end to end — discovery to a quantified spec, a solution narrative in the customer’s vocabulary, and a hero/problem/resolution demo that re-states the value — then defend it under pressure across the two-round solutions-engineer loop (architecture + discovery/demo).

• →Enterprise AI Architecture
• →Evaluation Design
• →Discovery and Value Selling