AI Engineer
- Hiring from
- Ireland
- Work type
- Hybrid
- Posted
613,903 remote jobs, straight from company career pages
100% free · New jobs every minute
Show job descriptionHide job description
Job Title: AI Engineer
Location: Cork, Dublin or Limerick, Ireland (Hybrid)
Duration: 6 months
Contract Type: Temp-to-Perm
We are looking for an experienced AI Engineer to join the team on a 6-month contract, with the potential to transition to a permanent position.
The ideal candidate will have strong hands-on experience building and deploying production-grade AI systems, particularly agentic AI, multi-agent architectures, RAG, and enterprise AI platforms. They should be comfortable leading technical design, building reusable engineering patterns, and improving the reliability, performance and scalability of AI solutions.
Candidates should be based in Ireland and able to work in a hybrid model from Cork, Dublin or Limerick.
Job Description
We are looking for an experienced AI Engineer to lead the design, development and delivery of production-ready AI systems. The ideal candidate will combine strong hands-on engineering skills with architectural thinking and technical leadership to build reliable, scalable and reusable AI solutions.
The role focuses on agentic AI, multi-agent systems, LLM-based applications, context and memory engineering, retrieval systems, AI evaluation and production AI platforms.
Key Responsibilities
- Design and build production-grade agentic AI and multi-agent systems.
- Develop agent orchestration, tool execution, state management, workflow, retry, fallback and recovery patterns.
- Build reliable agent workflows covering reasoning, action, observation, validation and termination.
- Design context, memory, retrieval and knowledge architectures for AI applications.
- Develop reusable AI capabilities, skills, plugins and integrations using technologies such as MCP and A2A.
- Build and maintain AI evaluation frameworks, testing harnesses, observability and production debugging processes.
- Apply software engineering best practices, including test-driven development (TDD), spec-driven development, Domain-Driven Design and API design.
- Design and develop scalable AI platforms and distributed systems.
- Optimise model inference, token usage, latency and operational costs.
- Implement LLMOps and AgentOps practices to support reliable production deployments.
- Explore multimodal AI capabilities involving text, images and voice.
- Collaborate with Product Managers, Architects, Engineers and subject matter experts to establish engineering standards and reusable patterns across teams.
- Contribute to technical roadmaps, platform reliability, serviceability and AI readiness.
Required Skills and Experience
- Strong hands-on experience in AI engineering, agentic AI, multi-agent systems and LLM-based application development.
- Strong software engineering background with experience building APIs and distributed systems.
- Experience with context engineering, memory architecture, Retrieval-Augmented Generation (RAG) and retrieval systems.
- Knowledge of graph technologies, including LPG, RDF, Knowledge Graphs and GraphRAG.
- Experience developing AI evaluation frameworks, testing harnesses and observability solutions.
- Familiarity with AI interoperability and tool integration, including MCP, A2A, plugins, skills and tool calling.
- Experience with LLMOps, AgentOps and deploying AI systems into production.
- Understanding of inference optimisation, model routing, token economics, latency and cost management.
- Experience with AI-assisted coding and agentic software development lifecycle (SDLC) practices.
- Understanding of AI user experience patterns, including AG-UI and human-in-the-loop workflows.
- Exposure to multimodal AI technologies involving voice, image and text.
- Strong technical leadership, problem-solving and communication skills.
- Ability to work independently and collaborate effectively across engineering teams.
What We're Looking For
- A hands-on AI Engineer who can take ownership of complex AI engineering challenges, make sound architectural decisions, build reliable production systems and establish reusable engineering practices across multiple teams.
