Senior AI Platform Engineer – Model Serving

Workday; Boulder (CO); Hybrid; USD 156,000 - 234,000; Full time

Job summary

Workday’s AI Model Serving team in Boulder is building the backbone for production AI workloads, hosting and scaling ML models. You’ll help shape the platform's vision, drive design decisions, and lead initiatives that push performance and reliability at scale.

You will collaborate across engineering and data science teams, mentor engineers, and contribute to a culture of high performance and inclusion, with a flexible work approach and strong focus on operational excellence.

Qualifications

• 6+ years of experience building and operating large-scale distributed systems.
• Bachelor's degree in Computer Science, Engineering, or related field.
• Deep experience designing, building, and scaling production-grade distributed systems.
• Proficiency in Python for production code.
• Hands-on experience with Kubernetes and GPU resource management.
• Familiarity with LLMs and traditional ML models in production.
• Strong observability and monitoring practices.
• Excellent written and verbal communication skills.
• Mentorship and collaboration across teams.

Responsibilities

• Lead technically by making critical design decisions that drive performance, reliability, and scalability across the platform.
• Design, implement, and maintain large-scale systems enabling production of ML models.
• Write design documents to build consensus for new components and enhancements.
• Evaluate and adopt new technologies within Workday and the industry.
• Troubleshoot, improve, and scale CI pipelines.
• Collaborate with software engineers, ML engineers, and data scientists.
• Respond to alerts and debug production issues to maintain platform health.
• Review pull requests and enforce code quality and security standards.
• Develop documentation to share knowledge with other engineers.

Skills

Distributed systems

Python

System design

DevOps / CI

Mentorship

Communication

Education

Bachelor's degree in Computer Science or related engineering field

Tools

Kubernetes

GPU infrastructure

vLLM

TGI

Ray Serve

Job description

Workday’s AI Model Serving team in Boulder is building the backbone for production AI workloads, hosting and scaling ML models. You’ll help shape the platform's vision, drive design decisions, and lead initiatives that push performance and reliability at scale.

You will collaborate across engineering and data science teams, mentor engineers, and contribute to a culture of high performance and inclusion, with a flexible work approach and strong focus on operational excellence.