AI Platform Engineer, Agentic Interfaces
Job description
AI Platform Engineer, Agentic Interfaces
This role centers on designing and operating the secure bridge between AI agents and IFS business capabilities. You will own the semantic layer and the control plane, ensuring that intelligent agents can work safely and effectively inside enterprise software. The position demands strong engineering fundamentals combined with specialized skills in agentic systems, knowledge graphs, and production-grade platform delivery.
About the role
You will architect and build the interfaces, semantic layer, and control mechanisms that allow AI agents to operate within IFS applications securely and reliably. Your responsibilities include modeling business capabilities, creating secure data pathways, and establishing governance so that agent actions remain observable, measurable, and trustworthy. You will translate complex enterprise requirements into robust technical solutions that enable new forms of automation and interaction.
Key facts
What you'll do
You will design and implement Model Context Protocol (MCP) servers that expose IFS business objects to agents in a discoverable and versioned manner. You will construct the semantic layer, combining an ontology with a knowledge graph derived from platform metadata and refined by industry context. Mapping user intent to precise operations will be achieved through a routing mechanism that selects the correct sequence of actions. You will build a secure write path that enables agents to modify customer data without risk. A strict control plane will enforce authentication, entitlements, agent identity, and a default-deny security posture. You will also create an evaluation harness that measures agent behavior against real product outcomes and drives continuous improvement. Rapid prototyping will validate emerging technologies, new product opportunities, and customer scenarios. Finally, you will define and enforce engineering practices for testing, observability, monitoring, governance, and operational excellence.
Requirements
You bring production experience in building and operating distributed, cloud-native enterprise systems. Expertise in API and schema design, event-driven architectures, security, observability, and CI/CD is essential. Strong programming ability in a modern backend language is required. Demonstrated experience delivering AI systems that use large language models, retrieval-augmented generation, agentic workflows, and orchestration frameworks is mandatory. You must understand the discipline of evaluation, using experimentation, benchmarking, and tracing to improve agent performance based on evidence. The ability to design solutions that integrate enterprise applications, business processes, workflows, and data platforms is critical. Depth in at least one specialized area is required, such as tool-surface and agent-runtime engineering, including MCP servers, tool ecosystems, capability modeling, and governance, or knowledge graphs and semantic modeling, including ontology design and grounding strategies. Enterprise platform depth, with experience in Oracle PL/SQL or OData within metadata-driven systems, is expected.
Nice to have
Experience using agent frameworks such as those referenced in this role description is valuable. Background in building reusable AI platforms that serve multiple products and teams is advantageous. Familiarity with containerized platforms and infrastructure automation using Docker and Kubernetes is beneficial. Experience with hyperscale cloud platforms such as Azure, AWS, or GCP supports scalable and resilient solutions. Capability in reverse engineering or interpreter work expands implementation flexibility. A focus on token-efficient agent design aligns with enterprise constraints. Knowledge of enterprise software domains such as asset management, service management, manufacturing, supply chain, aerospace and defense, energy, telecommunications, or construction is relevant.
Skills & tools
Model Context Protocol, Semantic Kernel, LangGraph, AutoGen, PydanticAI, OpenAI Agents SDK, CrewAI, Oracle PL/SQL, OData
Practical notes
Please About the company
IFS builds an enterprise-grade AI hiring platform for HR and recruiting teams. The system centralizes applicant tracking and supports an all-in-one workflow that coordinates sourcing, assessment, and hiring.
People in talent roles use the platform to manage open roles, schedule interviews, and move candidates through defined stages. The interface emphasizes clear data, structured feedback, and steady progress tracking for every recruiter.