AI Platform Engineer

About the role

This role focuses on building the AI platform that connects IFS enterprise software to large language models through Model Context Protocol servers and a semantic layer. You will design capability modelling, discoverability, versioning, and backward compatibility as first-class concerns while constructing a write path that lets agents safely modify customer operational data. The work spans a generated ontology and knowledge graph, a skills layer that maps requests to correct operation sequences, a router that selects between operations, and a control plane covering authentication, entitlements, agent identity, telemetry, metering, and injection resistance. You will also own an evaluation harness that certifies agent behaviour against the real product and drive improvements based on its measurements. Prototyping emerging technology, establishing engineering practices across evaluation, testing, observability, governance, and security, and representing the work externally through customer engagements and industry events complete the scope.

Key facts

What you'll do

• Design and build MCP servers over product business objects, treating capability modelling, discoverability, versioning, and backward compatibility as first-class design problems.
• Construct a write path enabling agents to safely change customer operational data.
• Build a semantic layer comprising an ontology and knowledge graph over the product, generated from platform metadata and curated industry by industry.
• Develop a skills layer that maps requests to correct operations and sequences, and a router that picks between operations.
• Implement a control plane covering authentication, entitlements, agent identity, telemetry, metering, and injection resistance with a default-deny posture.
• Build and maintain an evaluation harness that certifies agent behaviour against the real product, then improve the system against those measurements.
• Establish engineering practices spanning evaluation, testing, observability, monitoring, governance, security, and operational excellence.
• Create rapid prototypes and proofs of concept that validate emerging technology, product opportunities, and customer scenarios.
• Contribute to technical design, review other engineers' work, and support colleagues entering the domain.
• Represent work externally through customer engagements, demonstrations, industry events, and partner collaboration.

Requirements

• Production experience building and operating enterprise systems.
• Real depth in distributed systems, cloud-native architectures, API and schema design, event-driven systems, security, observability, and CI/CD.
• Strong programming in a modern backend language.
• Experience delivering AI systems built on LLMs, RAG, agentic workflows, and orchestration frameworks.
• Experience with tool use, function calling, workflow orchestration, and autonomous or multi-agent architectures.
• Judgement to know where AI systems fail.
• Evaluation as a discipline: experimentation, benchmarking, prompt engineering, tracing, quality measurement, and agent tuning.
• Ability to improve agents against evidence rather than impression.
• Ability to design solutions integrating enterprise applications, business processes, workflows, and data platforms.
• Depth in at least one of: tool-surface and agent-runtime engineering (MCP servers, tool ecosystems, capability modelling, discoverability, governance, versioning, backward compatibility, multi-tenancy isolation); knowledge graphs and semantic modelling (ontology design, context engineering, embeddings, vector databases, retrieval and search technologies, memory architectures, grounding strategies); or enterprise platform depth (Oracle PL/SQL, OData, comfort working inside large metadata-driven systems where behaviour is configured rather than coded).
• Demonstrable hands-on experience designing, building, and shipping production AI applications.

Nice to have

• Experience with agent frameworks: Semantic Kernel, Microsoft Agent Framework, LangGraph, AutoGen, PydanticAI, OpenAI Agents SDK, CrewAI.
• Experience building reusable AI platforms, MCP ecosystems, or shared engineering capabilities used across multiple products and teams.
• Containerised platforms and infrastructure automation: Docker, Kubernetes.
• Experience with Azure, AWS, GCP, or another hyperscale cloud platform.
• Reverse-engineering or interpreter work.
• Token-efficient agent design.
• Enterprise software domains: enterprise asset management, service management, manufacturing, supply chain, aerospace and defence, energy, telecommunications, construction, industrial AI.
• Contributions to open-source projects, technical communities, conferences, publications, or standards.

Engineering methods

Model Context Protocol (MCP), RAG, agentic workflows, orchestration frameworks, tool use, function calling, workflow orchestration, autonomous architectures, multi-agent architectures, evaluation, benchmarking, prompt engineering, tracing, quality measurement, agent tuning, distributed systems, cloud-native architectures, API design, schema design, event-driven systems, security, observability, CI/CD, Oracle PL/SQL, OData, metadata-driven systems, reverse-engineering, interpreter work, token-efficient agent design.

Relevant systems

IFS software, MCP servers, semantic layer, knowledge graph, skills layer, control plane, evaluation harness.

Practical notes

Hybrid

workplace: balance of remote and in-office working. Requires demonstrable hands-on experience designing, building and shipping production AI applications.