Applied AI Engineer

IFS; England; Hybrid; GBP 90,000 - 150,000; Full time

Job summary

IFS is building the next generation of AI-native enterprise software. You will design ontologies, knowledge graphs and grounding infra that let AI agents understand IFS software and reason over customer data to enable trusted, scalable automation.

Join a team delivering production AI systems across cloud-native architectures, with responsibilities spanning MCP servers, retrieval, grounding and governance. This role combines deep engineering with enterprise impact, in a hybrid work model across

Qualifications

• Production AI experience designing, building and shipping production AI applications.
• Experience delivering AI systems built on LLMs, retrieval-augmented generation and agentic workflows.
• Strong software engineering foundation for enterprise systems, including distributed systems and CI/CD.
• Experience designing and operating backend services in cloud-native environments.
• Ability to collaborate with domain experts to translate tacit knowledge into explicit models.

Responsibilities

• Design and build MCP servers (Model Context Protocol) over the product’s business objects with first-class handling of capability modelling, discoverability and versioning.
• Build the write path enabling agents to safely modify a customer’s operational data.
• Design and implement the semantic layer: ontology and knowledge graph, generated from platform data and curated by industry experts.
• Develop retrieval and grounding infrastructure connecting agents to knowledge: embeddings, vector databases, hybrid search and indexing strategies.
• Establish data quality, provenance and versioning for the knowledge graph to prevent drift in agent behaviour.
• Build the skills layer mapping requests to operations and sequences with a router to select between them.
• Create the control plane: authentication, entitlements, agent identity, telemetry, metering, and secure defaults.
• Develop evaluation harnesses to certify agent behaviour against the real product and drive improvements.
• Prototype rapidly through PoCs to validate technology opportunities and customer scenarios.
• Define engineering practices: testing, observability, governance and security for operational excellence.
• Contribute to technical design and peer reviews; support colleagues entering the domain.
• Represent the work to customers and partners through demos and collaborations.

Skills

AI systems design

Distributed systems

Backend programming

Cloud-native architectures

Knowledge graphs

Prompt engineering

Tools

Docker

Kubernetes

OpenAI API

LangGraph

Job description

At IFS, we're building the next generation of AI-native enterprise software, transforming how some of the world's largest organisations manage assets, operations and critical services.

This is an opportunity to work at the forefront of modern AI engineering, building intelligent products that combine Large Language Models (LLMs), agentic AI and cloud-native technologies to solve complex, real-world business challenges at enterprise scale.

We're looking for engineers who are passionate about building production AI systems and excited by the opportunity to shape the future of enterprise software.

Please note that this role requires demonstrable, hands-on experience designing, building and shipping production AI applications.

IFS is a billion-dollar revenue company with 6000+ employees on all continents. Our leading AI technology is the backbone of our award-winning enterprise software solutions, enabling our customers to be their best when it really matters–at the Moment of Service™. Our commitment to internal AI adoption has allowed us to stay at the forefront of technological advancements, ensuring our colleagues can unlock their creativity and productivity, and our solutions are always cutting-edge.

At IFS, we’re flexible, we’re innovative, and we’re focused not only on how we can engage with our customers but on how we can make a real change and have a worldwide impact. We help solve some of society’s greatest challenges, fostering a better future through our agility, collaboration, and trust.

We celebrate diversity and understand our responsibility to reflect the diverse world we work in. We are committed to promoting an inclusive workforce that fully represents the many different cultures, backgrounds, and viewpoints of our customers, our partners, and our communities. As a truly international company serving people from around the globe, we realize that our success is tantamount to the respect we have for those different points of view.

By joining our team, you will have the opportunity to be part of a global, diverse environment; you will be joining a winning team with a commitment to sustainability; and a company where we get things done so that you can make a positive impact on the world.

We’re looking for innovative and original thinkers to work in an environment where you can #MakeYourMoment so that we can help others make theirs. With the power of our AI-driven solutions, we empower our team to change the status quo and make a real difference.

If you want to change the status quo, we’ll help you make your moment. Join Team Purple. Join IFS.

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,versioningand 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 agentbehaviouragainst the realproduct, andimprove the system against what it measures.

• Build rapid prototypes and proofs of concept tovalidateemerging technology, productopportunitiesand customer scenarios.

• Establish the engineering practices these systems need: evaluation, testing, observability, monitoring, governance,securityand 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, industryeventsand 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,observabilityand CI/CD.

• Strong programming in a modern backend language.

• Experience delivering AI systems built on large language models, retrieval-augmented generation (RAG), agenticworkflowsand 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, qualitymeasurementand agent tuning, improving an agent against evidence rather than impression.

• Ability to design solutions that integrate enterprise applications, business processes,workflowsand 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 wherebehaviouris configured rather than coded.

Desirable

• Experience with agent frameworks such as Semantic Kernel, Microsoft Agent Framework,LangGraph,AutoGen,PydanticAI, the OpenAI Agents SDK orCrewAI.

• Experience building reusable AI platforms, MCP ecosystems or shared engineering capabilities used across multiple products and teams.

• Containerisedplatforms and infrastructure automation: Docker, Kubernetes.

• Experience with Azure, AWS,GCPor another hyperscale cloud platform.

• Reverse-engineeringor interpreter work.

• Token-efficient agent design.

• Enterprise software domains: enterprise asset management, service management, manufacturing, supply chain, aerospace anddefence, energy, telecommunications, construction, industrial AI.

• Contributions to open-source projects, technical communities, conferences,publicationsor standards.

We believe that coming together as a community, in person, is important for innovation, connection and fostering a sense of belonging. Our roles have the right balance of remote and in-office working to enable flexibility for managing your life along with ensuring a real connection with your colleagues and the broader IFS community.