Role: Principal AI Agent Engineer
Duration: 12 months + extension (long term project)
Engagement: Contract/freelance (full time, 5 days per week, 8 hour days)
Location: Onsite in Cork 3-4 days per week, remaining remote
General Summary: This position exists to lead the design, development, and deployment of advanced AI agent systems that solve complex business problems through autonomous reasoning and decision-making capabilities. The Principal AI Agent Engineer will architect scalable agentic solutions, establish technical standards, and drive innovation in multi-agent systems and autonomous workflows. This role is critical to advancing the organization's AI capabilities and delivering high-impact intelligent automation solutions.
Duties & Responsibilities:
Design and implement production-grade AI agent architectures using large language models, reasoning frameworks, and tool-use capabilities 30%
Lead technical strategy for agentic AI systems, including multi-agent orchestration, memory systems, and autonomous workflow design 25%
Develop and optimize agent evaluation frameworks, performance metrics, and quality assurance processes for autonomous systems 15%
Collaborate with cross-functional teams to identify use cases, define requirements, and integrate AI agents into enterprise systems 15%
Research and prototype emerging agentic AI technologies, frameworks, and methodologies to maintain technical leadership 10%
Mentor engineers and data scientists on agentic AI best practices, design patterns, and implementation strategies 5%
Knowledge, Skills and Abilities (KSAs):
Deep expertise in large language models (LLMs), prompt engineering, and agentic AI frameworks (e.g., LangChain, AutoGen, CrewAI)
Strong software engineering skills with proficiency in Python and experience building production-grade AI systems
Advanced understanding of agent reasoning patterns including ReAct, chain-of-thought, tree-of-thought, and reflection
Knowledge of vector databases, retrieval-augmented generation (RAG), and knowledge management systems
Ability to design and implement complex multi-agent systems with coordination, communication, and task delegation
Experience with cloud platforms (AWS, Azure, GCP) and MLOps practices for deploying and monitoring AI agents
Strong problem-solving skills with ability to translate business requirements into technical agent architectures
Excellent communication skills to explain complex agentic AI concepts to technical and non-technical stakeholders
Understanding of responsible AI principles, including safety, alignment, and ethical considerations for autonomous systems
Work Experience &/or Education:
Bachelor's degree in Computer Science, Engineering, or related technical field required; Master's or Ph.D. preferred
Minimum 7 years of software engineering experience with at least 3 years focused on AI/ML systems
Demonstrated experience building and deploying AI agents or autonomous systems in production environments
Track record of technical leadership in AI/ML projects with measurable business impact
Experience with modern LLM APIs (OpenAI, Anthropic, Google, etc.) and agentic frameworks required
Publications, open-source contributions, or speaking engagements in AI/ML community preferred