AI Platform Engineering Lead; Senior Manager

Position: AI Platform Engineering Lead (Senior Manager)
Location:

Anywhere in Country

At EY, we're all in to shape your future with confidence.

We'll help you succeed in a globally connected powerhouse of diverse teams and take your career wherever you want it to go.  Join EY and help to build a better working world.

** The opportunity*
* We are seeking a senior leader for our AI Platform Engineering group, the team that builds and operates the foundational substrate powering EY's AI-native platform. This role is accountable for the infrastructure and cloud-native platform layers of our AI runtime, from bare-metal and GPU infrastructure through Kubernetes, cluster fabric, secure inference, and multi-tenant scaling. You will set the technical direction for a team of AI Infrastructure and AI Systems Engineers, and be accountable for standing up and running EY AI environments across cloud, on-prem, edge, client-managed, and air-gapped targets.

This is a player-coach role. You will direct the team's work and own the delivery roadmap, while remaining a hands-on individual contributor who personally designs, builds, and troubleshoots the most critical and complex parts of the platform. The role is ideal for a senior engineering leader who is as comfortable troubleshooting a cluster configuration as they are in leading an executive review, who can set a phased roadmap and hold delivery gates under pressure, who treats reliability and portability as non-negotiable in regulated client contexts, and who understands that the substrate is a product in its own right, measured by the velocity, safety, and portability it unlocks for every team building above it.

** Your key responsibilities*
* +  
** Lead and develop the AI Platform Infrastructure Engineering team:
** direct the day-to-day and longer-term work of AI Infrastructure and AI Systems Engineers, set priorities, allocate work, and remove blockers so the team delivers predictably; hire, mentor, and coach engineers, set engineering standards (design reviews, code reviews, runbooks), and grow technical depth and leadership capability across the team.

+  
** Build hands-on as a senior individual contributor:
** personally design, implement, and debug the hardest and highest-risk components of the platform - cluster bring-up, GPU and networking enablement, multi-tenancy, inference and routing - and lead by example on engineering quality.

+  
** Own the infrastructure delivery roadmap:
** sequence the build into phases that each put a usable capability into engineering teams' hands, define and defend entry and exit gates, and report progress, risk, and trade-offs to senior leadership.

+  
** Own the infrastructure foundation and cloud-native platform:
** from Ubuntu/OS, BMC/bare-metal, DPU architecture, and NVAIE (GPU/Network/DCGM) through compute, Kubernetes and scheduling, cluster fabric and networking, multi-tenancy, and distributed compute - delivering foundational capabilities (Infrastructure Management, Kubernetes & Scheduling, Cluster Fabric Management) as a provisioned, patched, production-ready substrate for Agentic AI workflows and downstream runtime, data, and execution services.

+  
** Stand up and operate EY Agentic AI environments:
** across cloud (EKS/AKS/GKE), on-prem AI Factory (RKE2/NVAIE), edge (K3s), client-managed, and air-gapped deployment modes, maintaining one consistent stack contract across all targets and keeping the substrate modular and swappable so components can be replaced without rewriting consumers or creating vendor lock-in.

+  
** Own secure execution, inference, and routing:
** Ray Serve, vLLM/NIM/Triton, and NVIDIA Dynamo, with sandboxed execution (NVIDIA Open Shell) for isolated, safe model execution; and Envoy AI Gateway, semantic routing (vLLM-SR), model and prompt selection, and streaming response handling - directing each request to the right model under the right constraints.

+  
** Own operational excellence, resilience, and platform delivery:
** define SLOs, on-call and incident management practices, and lead post-incident reviews; own backup, disaster recovery, and cross-environment replication for high availability (Velero, CloudNative PG, Cilium Cluster Mesh), patching, security hardening, and supply-chain hygiene; and partner with Dev Ops Engineers on CI/CD/CV (ArgoCD) and infrastructure-as-code / Git Ops (Helm/Open Tofu) so environments are reproducible and drift-free.

+  
** Own GPU capacity, platform economics, and vendor selection:
** forecast demand, set quotas and cost attribution, and manage the…