Build and operate the interface, semantic layer and controls that let AI agents work inside IFS software safely.  Key responsibilities  Design and build MCP servers (Model Context Protocol, the emerging standard for exposing application capability to agents) over the product’s business objects, treating capability modelling, discoverability, versioning and backward compatibility as first-class design problems.  Build the write path that lets an agent safely change a customer’s operational data.  Build the semantic layer: an ontology and knowledge graph over the product, generated from what the platform already knows about itself and then curated industry by industry.  Build the skills layer that maps what someone asks for onto the correct operation and the correct sequence, with a router that picks between them.  Build the control plane: authentication, entitlements, agent identity, telemetry, metering, resistance to injection, and a default that denies rather than permits.  Build the evaluation harness that certifies agent behaviour against the real product, and improve the system against what it measures.  Build rapid prototypes and proofs of concept to validate emerging technology, product opportunities and customer scenarios.  Establish the engineering practices these systems need: evaluation, testing, observability, monitoring, governance, security and operational excellence.  Contribute to technical design, review other engineers’ work, and support colleagues coming into the domain.  Represent the work outside the team through customer engagements, demonstrations, industry events and partner collaboration.