Principal AI Engineer

Workday•Vancouver, BC

1d•$206,000 - $370,000•Hybrid

About The Position

As a Principal AI Engineer in Agent Factory, you will lead the end-to-end system design, architectural framework, and product integration of Workday’s next generation of intelligent agents. While our ML Engineers focus on building, training, and optimizing foundational algorithms, your mission is intelligence orchestration and product delivery—connecting the brain to the product. Sitting at the intersection of AI capabilities, enterprise platforms, and human workflows, you will architect how foundational models are safely and reliably integrated into functional, production-grade software. You will own the design, experimentation, and orchestration of complex agentic workflows, translating cutting-edge AI capabilities into enterprise-grade business value. Because these agents interact with sensitive HR and financial data at a global scale, you will be a core champion for Responsible and Governed AI—architecting systems with strict guardrails for data privacy, predictability, and explainability. This role requires a balance of high-level system design and hands-on execution, solving critical product constraints like latency, cost, and reliability.

Requirements

10+ years of professional software engineering experience with deep expertise in distributed systems, cloud computing, and API design, plus 2+ years of dedicated focus building production-grade LLM/agentic systems OR 7+ years of experience specifically within Machine Learning Engineering or AI application development, with 3+ years dedicated to shipping LLM-backed products.
3+ years of hands-on experience integrating large models (LLMs, Foundation Models) and modern AI APIs into user-facing enterprise products.
2+ years of experience designing and scaling complex AI orchestration architectures—including multi-agent frameworks, routing layers, and advanced RAG pipelines.
6+ years of experience optimizing application performance (specifically tackling constraints like API latency and user interaction design), with 2+ years applied to modern LLM constraints (such as token management, cost optimization, and context-window efficiency).
6+ years of proven experience leveraging cloud computing platforms (e.g., AWS, GCP) to deploy highly responsive, scalable systems.
Deep understanding of how to implement governance, guardrails, security layers, and evaluation mechanisms necessary when deploying autonomous agents over sensitive enterprise HR and financial data.
Deep focus on business value, user experience, and applying deep learning/large models directly to solve practical end-user challenges.
Expert-level ability to architect robust application layers that wrap around AI models, ensuring system predictability, error handling, and seamless UX integration.
Skilled in rapid prototyping, benchmarking model outputs against product requirements, and managing continuous experimentation cycles for agentic behavior.
Highly autonomous leader capable of taking complex, open-ended product goals and turning them into scalable, concrete engineering realities.

Nice To Haves

Master’s degree in Computer Science, Software Engineering, or equivalent technical field.
Proven track record of technically leading cross-functional pods, mentoring senior engineers, and steering the product development lifecycle from abstract concept to successful deployment.

Responsibilities

Lead the end-to-end system design, architectural framework, and product integration of Workday’s next generation of intelligent agents.
Architect how foundational models are safely and reliably integrated into functional, production-grade software.
Own the design, experimentation, and orchestration of complex agentic workflows.
Translate cutting-edge AI capabilities into enterprise-grade business value.
Architect systems with strict guardrails for data privacy, predictability, and explainability.
Solve critical product constraints like latency, cost, and reliability.
Technically lead cross-functional pods.
Mentor senior engineers.
Steer the product development lifecycle from abstract concept to successful deployment.
Architect robust application layers that wrap around AI models, ensuring system predictability, error handling, and seamless UX integration.
Manage continuous experimentation cycles for agentic behavior.