AI Engineer

Company Description

We are in Business for People, empowering people in service organizations with innovative Enterprise and Business software solutions. We’ve innovated and taken a new approach to delivering ERP that works for people. Self-driving, adaptive and intuitive software that is changing the way people work. Our solutions empower people and deliver a better people experience so people can spend time on meaningful high value work they live for.

Job Description

We are seeking a highly skilled and forward-thinking AI Engineer to join our AI research team for ERP. This role plays a pivotal part in shaping the future of enterprise software by designing, developing, and deploying AI systems, intelligent agents, and orchestration frameworks, while also focusing on streamlining the deployment, monitoring, and continuous improvement of AI solutions (e.g., MLOps, LLMOps). You will operate at the frontier of the AI landscape, where your work will directly influence how enterprise software evolves into an AI-native platform. By enabling intelligent agents to reason, act, and collaborate—driving automation, adaptability, and next-generation business intelligence. Your primary responsibility will be AI research that supports intelligent automation and orchestration within enterprise systems. Additionally, your expertise will play a vital role in advancing current and future AI engineering initiatives across multiple teams and projects at Unit4.

Key Responsibilities:

Generative AI Foundations

• Design and implement GenAI solutions using LLMs and RAG capabilities such as Search and Retrieval or GraphRAG.
• Define and enforce best practices for prompt templates, advanced prompting engineering, and context-aware prompting.
• Contribute to the evolution of the Unit4 AI Foundation platform.
• Collaborate on the design and implementation of LLM evaluation frameworks, benchmarks, and performance metrics.

Agentic Architecture & Orchestration

• Build modular, task-specific agents using frameworks like Semantic Kernel or similar.
• Define best practices for agent tooling on the Unit4 ecosystem using existing standards such as Model Context Protocol (MCP).
• Implement agent orchestration protocols (e.g., A2A) for multi-agent collaboration.
• Develop adaptive planning engines aligned with user workflows and business processes.
• Collaborate on the design and implementation of agent evaluation frameworks, benchmarks, and performance metrics.

Infrastructure & Deployment

• Design cloud-native, scalable infrastructure for agent workloads (Azure, AWS, GCP).
• Build robust pipelines for AI deployment and lifecycle management—combining MLOps and LLMOps practices with CI/CD and Infrastructure as Code (e.g., Terraform, Bicep).
• Ensure observability, monitoring, and feedback loops for agent performance and reliability.

Data Integration & Event-Driven Systems

• Collaborate with data engineers and architects to integrate structured and unstructured data sources.
• Leverage event-driven architectures (e.g., Kafka, Flink) for real-time agent actions.
• Define data contracts and schemas to support agentic decision-making.

Collaboration & Leadership

• Work closely with architects, data scientists, data engineers, and product leads to align AI foundational architecture with business goals.
• Participate in design and architectural reviews, roadmap planning, and research cross-functional discussions.
• Mentor junior engineers and contribute to knowledge sharing across teams.

Requirements:

Technical Skills

GenAI Foundations

• Proficiency in leveraging Language Models (e.g., LLMs, SLMs), Retrieval-Augmented Generation (RAG), and prompt engineering.

Infrastructure & Deployment

• Experience with design and imple