Design and maintain prompt architecture for production agents — system prompt structure, few-shot example design, structured output schemas, prompt versioning, and A/B testing of prompt changes as production artefacts.
Design and implement the agent harness: agent instantiation, persona and instruction loading, tool binding, memory initialisation, and lifecycle management from invocation to termination.
Architect multi-agent orchestration topologies — supervisor/worker hierarchies, event-driven graphs, parallel execution — with defined A2A handoff contracts, shared state schemas, and structured escalation paths....
Define the client's AI transformation roadmap — prioritising initiatives by strategic value and execution readiness, managing board-level change, and ensuring sustainable adoption of agentic AI across the organisation.
Set architecture principles and make consequential technology choices for enterprise agentic AI programmes — spanning agent harness design, orchestration patterns, knowledge layer strategy, trust and safety frameworks, and AgentOps discipline; maintain sufficient hands-on depth to challenge assumptions, evaluate trade-offs, and direct senior engineers credibly.
Govern technical standards across the portfolio: orchestration and A2A patterns, knowledge layer architecture (RAG, MCP, Text-to-SQL, knowledge graphs), evaluation frameworks (golden datasets, LLM-as-judge, trajectory evals), and production readiness criteria — ensuring engineering disciplines are institutionalised, not improvised....