Applied AI Engineer

Ifs1; Greater London; In loco; GBP 110.000 - 190.000; Tempo pieno

Descrizione del lavoro

IFS is seeking a senior engineer to build and curate the ontology, knowledge graph and grounding infrastructure that let AI agents understand the software and reason over customer data.

You will design MCP servers, the semantic layer, and robust retrieval/ grounding systems, while ensuring data provenance and secure operation across enterprise-scale platforms.

Competenze

• Experience delivering AI systems with LLMs and retrieval-augmented generation (RAG).
• Strong background in knowledge graphs, ontology design and schema evolution.
• Proven ability to design scalable enterprise platforms and secure, observable systems.
• Hands-on backend engineering with API design and cloud-native architectures.

Mansioni

• Design and build MCP servers (Model Context Protocol) over product objects with versioning and compatibility in mind.
• Build the write path enabling agents to modify customer operational data safely.
• Design the semantic layer: ontology and knowledge graph built from platform knowledge and domain expertise.
• Create retrieval and grounding infrastructure: embeddings, vector databases, hybrid search, memory and grounding.
• Establish data quality, provenance and versioning for the knowledge graph.
• Develop the skills layer mapping requests to operations and a routing mechanism.
• Build the control plane: authentication, entitlements, agent identity and security.
• Develop evaluation harnesses to certify agent behaviour against real product data.
• Create rapid prototypes to validate emerging tech, opportunities and customer scenarios.
• Establish engineering practices: testing, observability, governance and operational excellence.
• Contribute to technical design, review peers and support teammates entering the domain.
• Represent work externally through customer engagements, demonstrations and events.

Conoscenze

MCP servers

Capability modelling

Distributed systems

API design

CI/CD

Knowledge graphs

Security & governance

Cloud-native

Code reviews

LangGraph / Semantic Kernel

Strumenti

Docker

Kubernetes

Semantic Kernel

Microsoft Agent Framework

LangGraph

OpenAI Agents SDK

CrewAI

Oracle PL/SQL

OData

Descrizione del lavoro

Build and curate the ontology, knowledge graph and grounding infrastructure that let AI agents understand IFS software and reason accurately over customer data, turning what the platform already knows about itself, plus deep industry expertise, into a semantic layer other engineers and agents can trust.

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.
• Design and 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, in partnership with domain experts who turn tacit product knowledge into an explicit, machine-usable model.
• Build the retrieval and grounding infrastructure that connects agents to this knowledge: embeddings, vector databases, hybrid search, chunking and indexing strategies, memory architectures, and grounding techniques that keep agent outputs accurate and traceable to source.
• Establish data quality, provenance and versioning practices for the knowledge graph, so changes are traceable and agent behaviour built on top of it doesn't silently drift.
• 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.

Strong software engineering first. Everything else is applied on top of that.

Production experience building and operating enterprise systems, with 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 large language models, retrieval-augmented generation (RAG), agentic workflows and orchestration frameworks, including tool use, function calling, workflow orchestration and autonomous or multi-agent architectures, with the judgement to know where they fail.

Deep, hands-on expertise in knowledge graphs and semantic modelling: ontology design (RDF/OWL/SKOS or property-graph equivalents), taxonomy and controlled-vocabulary design, entity resolution, schema evolution and versioning, embeddings, vector databases and grounding strategies.

Evaluation as a discipline: experimentation, benchmarking, prompt engineering, tracing, quality measurement and agent tuning, improving an agent against evidence rather than impression.

Ability to design solutions that integrate enterprise applications, business processes, workflows and data platforms.

Comfort working directly with domain experts to translate tacit business knowledge into explicit, machine-usable models.

Depth in at least one of the following:

• Tool-surface and agent-runtime engineering. MCP servers, tool ecosystems, capability modelling, discoverability, governance, versioning, backward compatibility, multi-tenancy isolation.
• Enterprise platform depth. Oracle PL/SQL, OData, and comfort working inside 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.
• 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.

We believe that coming together as a community, in person