AI Platform Engineer, Agentic Interfaces

Description

The role covers the interface, semantic layer and controls that let AI agents work safely inside the company's software.

The company builds AI-native enterprise software for large organisations that manage assets, operations and critical services, using LLMs, agentic AI and cloud-native technology.

It has billion-dollar revenue and 7000+ employees across all continents, works internationally and is committed to sustainability.

Responsibilities

• Design and build MCP servers, the emerging Model Context Protocol standard for giving agents access to application capability, over the product's business objects. Treat capability modelling, discoverability, versioning and backward compatibility as core design problems.
• Build the write path that lets an agent change a customer's operational data safely.
• Build the semantic layer: an ontology and knowledge graph over the product. Generate it first from what the platform already knows about itself, then curate it industry by industry.
• Build the skills layer that maps a request to the right operation and sequence, plus a router that chooses between them.
• Build the control plane: authentication, entitlements, agent identity, telemetry, metering, injection resistance, and deny-by-default access.
• Build the evaluation harness that checks agent behaviour against the real product, and use its results to improve the system.
• Build quick prototypes and proofs of concept to test emerging technology, product ideas and customer scenarios.
• Set up the engineering practices these systems need: evaluation, testing, observability, monitoring, governance, security and operational excellence.
• Take part in technical design, review other engineers' work, and help colleagues new to the domain.
• Represent the team externally through customer engagements, demonstrations, industry events and partner work.

Requirements

• Solid software engineering is the base. AI work is built on top of it.
• Production experience building and running enterprise systems, with depth in distributed systems, cloud-native architecture, API and schema design, event-driven systems, security, observability and CI/CD.
• Strong programming skills in a modern backend language.
• Hands-on experience with LLM-based AI systems, retrieval-augmented generation (RAG), agentic workflows and orchestration frameworks. This covers tool use, function calling, workflow orchestration, and autonomous or multi-agent designs, and knowing where they fail.
• Evaluation as a working discipline: experiments, benchmarks, prompt engineering, tracing, quality measurement and agent tuning, guided by evidence.
• Ability to design solutions that connect enterprise applications, business processes, workflows and data platforms.
• Depth in at least one of the following areas:
• Tool-surface and agent-runtime engineering: MCP servers, tool ecosystems, capability modelling, discoverability, governance, versioning, backward compatibility and multi-tenancy isolation.
• Knowledge graphs and semantic modelling: ontology design, context engineering, embeddings, vector databases, retrieval and search, memory architectures and grounding strategies.
• Enterprise platform work: Oracle PL/SQL, OData, and comfort in large metadata-driven systems where behaviour is configured rather than coded.
• Desirable: experience with agent frameworks such as Semantic Kernel, Microsoft Agent Framework, LangGraph, AutoGen, PydanticAI, the OpenAI Agents SDK or CrewAI.
• Desirable: experience building reusable AI platforms, MCP ecosystems or shared engineering capabilities used by several products and teams.
• Desirable: containerised platforms and infrastructure automation with Docker or Kubernetes.
• Desirable: experience with Azure, AWS, GCP or another hyperscale cloud platform.
• Desirable: reverse-engineering or interpreter work.
• Desirable: token-efficient agent design.
• Desirable: work in enterprise software domains such as enterprise asset management, service management, manufacturing, supply chain, aerospace and defence, energy, telecommunications, construction or industrial AI.
• Desirable: contributions to open-source projects, technical communities, conferences, publications or standards.

Conditions

The role is hybrid, so you can work in a way that suits you while staying connected with colleagues.

The company values diverse perspectives and an inclusive workplace.