Senior AI Platform DevOps Engineer – NYC Hybrid

DoubleVerify

Northern, New York (KY, NY)

Hybrid

USD 153,000 - 260,000

Full time

8 days ago

Application generator

Don’t send a generic resume — generate a resume and cover letter tailored to this exact role.

Get past ATS filters

Benefits offered by this job

Bonus / equity

Benefits

Hybrid work

Job summary

DoubleVerify is seeking a Sr. DevOps Engineer II for its AI Platforms team in New York City. The role focuses on running and hardening the MCP gateway, advancing IAM and access control, and consolidating gateway deployments to GA with multi-region failover.

You will work across a distributed team to ensure secure, observable AI infrastructure at scale. The candidate brings 5+ years in DevOps/SRE, hands-on experience with AI infrastructure in production, and strong expertise in OAuth, JWT, and

Qualifications

5+ years in DevOps, Platform Engineering or SRE with production Kubernetes ownership.
Hands-on experience managing and scaling AI infrastructure in production.
Deep knowledge of OAuth 2.0/2.1, OIDC and JWT with token exchange and scope design.
Experience with gateway, proxy or service mesh (Envoy or equivalent).
Track record taking infrastructure from prototype to GA, with SLOs and failover.
Strong collaboration in a distributed engineering group.

Responsibilities

Run and harden the MCP gateway day to day on Envoy Gateway in GKE.
Lead on closing the authorization gap: group-based access from JWT claims, per-tool RBAC, OAuth scopes.
Consolidate the model gateway estate to GA with multi-region, health-checked failover.
Advance AI observability and extend the trace pipeline across tools for cost and latency metrics.
Build infrastructure for AI cost governance: spend caps, attribution, alerts.
Support the registry, eval and marketplace platform and collaborate with Security on access control and supply chain review.