AI Engineer (Cork, Ireland)

Role

Responsibilities

• Design, prototype, and productionise AI systems including LLM-based agents, retrieval-augmented generation (RAG) pipelines and AI-driven workflows.

• Integrate and orchestrate LLMs (e.g. OpenAI, Anthropic, or custom fine-tuned models) using frameworks such as LangGraph, PydanticAI and Model Context Protocol (MCP).

• Build AI evaluation and feedback loops to ensure high-quality, reliable model behaviour in production.

• Collaborate with software engineers and product managers to integrate AI features into user-facing products with strong monitoring, resilience, and measurable user value.

• Experiment, measure, and iterate from prompt design and model selection to API optimization, latency, and cost trade-offs.

• Contribute to AI platform infrastructure: data pipelines, embedding, vector stores, model deployment and observability.

• Stay current with AI research and apply emerging techniques that improve reasoning, grounding, and reliability in multi-agent systems.

• Take a hands-on approach to shipping high-quality code incrementally, we value learning through iteration over aiming for perfection upfront.

• Participate in code reviews and architecture discussions to ensure technical excellence and knowledge sharing.

• Work closely with the Product team to shape features that are valuable, feasible, and grounded in users needs.

• Assist and mentor junior team members.

Your profile

• Strong experience (5+ years) in Python and backend systems, ideally within a SaaS or data-rich product environment.

• Deep understanding of LLM-based systems, including prompt engineering, retrieval augmentation, evaluation and model integration.

• Hands-on experience with AI orchestration frameworks (LangChain, LangGraph, PydanticAI or similar).

• Familiarity with ML pipeline tooling and deployment an advantage (e.g., vector databases, embeddings, Docker, AWS ECS, Pulumi etc.)

• Strong software engineering practices like version control, CI/CD, observability, and testing of AI-enabled systems.

• Awareness of LLMOps best practices, from managing API costs to monitoring model drift and user satisfaction.

• A product mindset: balancing experimentation with delivering business value to users.

• Curiosity and initiative you’re motivated by discovery, iteration and seeing ideas reach production.

• Collaborative spirit and excellent communication, your comfortable working across disciplines (Engineering, Product, Design, and Data Science).

• You thrive in an environment of mutual respect, openness and collaboration. You enjoy getting things done at a quick pace.

Why us?

Here at Keelvar, we are proud to be a remote-first organisation and we offer some great perks.

• Competitive salary with a Series B backed, fast growing organisation
• 25 days holidays increasing to 26 after 3 years and increasing again to 27 after 5 years. Plus your birthday off on us
• Flexible working hours with a positive approach to work - life balance
• An inclusive, collaborative, innovative culture
• Generous leave offerings including Wellbeing days
• Technology that enables you to perform to your best

If you really like the sound of the role but don't match every listed criteria exactly, we still want to hear from you. You could be the exact fit for this or any of our other roles.

We are also a diverse group and we intend to continue to attract and retain diverse talent in our organisation. We're committed to an inclusive and diverse Keelvar. We do not discriminate based on gender, ethnicity, sexual orientation, religion, civil or family status, age, disability, or race.

Position ID

1081285