Senior AI Engineer — Hybrid/Remote, Scalable AI

Workday; Dublin; Hybrid; EUR 91,000 - 137,000; Full time

Job summary

Workday is seeking an AI Engineer to develop tailored user experiences using advanced LLMs, agentic development, RAG, and knowledge graphs. You will collaborate with engineers to deploy AI pipelines across Workday's product ecosystem and leverage cloud computing resources to deliver scalable AI solutions.

The role emphasizes continuous improvement, quality, security, and ownership, with a strong product mindset and evidence-based evaluation of model outputs.

Qualifications

• 8+ years of professional experience in software engineering and product-building, with a proven track record of shipping and maintaining production code at scale.
• 3+ years of hands-on experience integrating large models (LLMs) into enterprise products.
• 2+ years building with modern AI orchestration frameworks and implementing prompt engineering for agentic workflows.

Responsibilities

• Develop tailored user experiences using LLMs, agentic development, RAG, and knowledge graphs.
• Collaborate with engineers to deploy AI pipelines across Workday's product ecosystem.
• Ensure performance, scalability, and security in AI features.
• Maintain observability and code quality with automated tests and monitoring.

Skills

Software engineering

Product-building

LLMs integration

AI orchestration

Performance optimization

Cloud deployment

Python

Education

Bachelor's degree

Master's degree preferred

Tools

LangChain

LlamaIndex

multi-agent frameworks

Prometheus/Grafana

OpenTelemetry

Sentry

Datadog

Job description

Workday is seeking an AI Engineer to develop tailored user experiences using advanced LLMs, agentic development, RAG, and knowledge graphs. You will collaborate with engineers to deploy AI pipelines across Workday's product ecosystem and leverage cloud computing resources to deliver scalable AI solutions.

The role emphasizes continuous improvement, quality, security, and ownership, with a strong product mindset and evidence-based evaluation of model outputs.