Join EY's Managed Services "AI for AI" team as an AI Platform Engineering Manager and drive the deployment and scaling of cutting-edge agentic AI solutions. This role is pivotal in managing a hybrid infrastructure encompassing multi-cloud, on-prem, and hosted model environments. You will lead a team dedicated to transforming AI prototypes into robust, enterprise-grade platforms that operate globally with security and cost-efficiency.

This position integrates platform engineering, MLOps/LLMOps, and agentic systems architecture to build resilient and scalable AI solutions for EY's diverse client needs.

Your core responsibilities will include owning the platform deployment for agentic AI solutions across major cloud providers (AWS, Azure, GCP), on-premise, and hybrid environments. You will design and manage CI/CD and MLOps/LLMOps pipelines for seamless model deployment, versioning, and continuous evaluation.

Key tasks involve architecting for high availability, managing a team of engineers, and collaborating cross-functionally to translate AI workflows into production-ready systems. You'll also manage model-hosting strategies, build observability for agentic systems, and drive security and compliance in AI infrastructure, especially for regulated clients.

We seek candidates with 5-8 years of experience in platform engineering, infrastructure/DevOps, SRE, or MLOps, including at least 2 years focused on production AI/ML or LLM systems. Demonstrated success in deploying and scaling platforms across multiple cloud providers and hybrid environments is essential.

Proficiency in Infrastructure-as-Code tools (Terraform, Pulumi, CloudFormation) and experience with Kubernetes, Docker, and CI/CD tooling are required. Familiarity with MLOps/LLMOps tools, model-hosting economics, GPU resource management, and enterprise security requirements is crucial. Strong leadership and cross-functional collaboration skills are paramount for this role, particularly the ability to thrive in a build-from-scratch environment.