AI Systems Engineer - DevOps& Observability - Senior

AI Systems Engineer

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 an AI Systems Engineer to own the delivery, model-serving, routing, and observability layer of EY's AI-native platform. These are the systems that ship, run, and make fully visible every AI workload. Within the Hybrid AI Multi-Environment Runtime (HAI), this role advised how AI services and agents are built and deployed, how models execute, how requests are routed to them, how AI assets are catalogued and governed, how consumption is measured and bounded, and how the entire platform is observed across cloud, on-prem, edge, and air-gapped environments.

Works with senior engineers to test and develop capabilities.

This role is ideal for an engineer who is equally comfortable building automated delivery pipelines, operating high-performance inference (GPUs, model servers, sandboxed execution), and building deep observability and cost visibility; who understands that in regulated contexts every AI workload must be delivered repeatably and every AI request must be economically bounded, attributable, and traceable end-to-end.

Your key responsibilities

+ Supports Dev Ops and delivery for AI workloads: build and operate the CI/CD/CV pipelines that ship AI services, agents, and runtime components, including automated build, test, continuous verification, release, and rollback, so AI workloads are delivered repeatably and safely into every environment.

+ Own governance and discovery for AI assets, including service catalog/registry (Artifactory/Nexus, Harbor), experiment tracking and model metadata (MLflow), upstream registries/mirrors (Hugging Face/ NGC ), CVE / SBOM scanning (Trivy), lineage contracts (Open Lineage), and license management.

+ Own resource and cost management, including quotas and rate limits, cost attribution and utilization (Apptio/Open Cost/Kubecost), so AI execution stays economically bounded and controllable per tenant and engagement.

+ Own the full observability stack, including metrics (Prometheus/Mimir), logs (Loki), traces (Tempo/Jaeger), dashboards (Grafana), LLM debugging and evaluation (Lang Smith/Langfuse), and SLA /alert notifications.

+ Own the Open Telemetry collection layer, including multi-tenant receiver, exporters and queues (Kafka sink), DCGM exporter for GPU telemetry, processor batching, and dynamic filtering, so every signal is captured and routed reliably.

+ Automate Git Ops-based delivery and continuous verification; embedding quality, integrity, and cost gates into pipelines so releases are policy-compliant by default rather than by manual review.

+ Close the loop between delivery and observability by using telemetry, evaluation, and cost signals to drive deployment decisions, progressive rollout, and automated rollback of AI workloads.

+ Ensure cost and telemetry are identity-stamped and per-tenant, so consumption and behavior are attributable end-to-end, keeping Fin Ops and observability tied to the workloads that generate the load.

Skills and attributes for success

+ Strong Dev Ops expertise: CI/CD/CV pipeline design, Git Ops, continuous verification, and progressive/automated release and rollback for production workloads.

+ Deep expertise operating model-serving and inference systems (Ray, vLLM/Triton/ NIM ) on GPUs at production scale.

+ Deep observability skills: metrics, logs, traces, and Open Telemetry.

+ Fin Ops mindset: able to attribute, bound, and optimize AI consumption cost per tenant and workload.

+ Familiarity with model/artifact governance, registries, CVE scanning, and license/lineage tracking.

+ Comfortable operating across cloud, on-prem, edge, and air-gapped environments with consistent runtime and telemetry semantics.

+ Strong communicator able to explain runtime, cost, and observability tradeoffs to engineers, architects, and leadership.

To qualify you must have

+ 8+ years in Dev Ops, MLOps, platform, or observability engineering, with hands-on production ownership of AI or high-throughput services.

+ Strong hands-on Dev Ops experience, including CI/CD/CV pipelines and Git Ops tooling (ArgoCD, Helm, Git Hub Actions/Git Lab CI, or equivalents) for automated build, test, release, and rollback.

+ Hands-on expertise operating inference/model-serving frameworks (Ray Serve, vLLM, Triton, or NIM ) on GPU infrastructure.

+ Strong experience with observability stacks (Prometheus, Grafana, Loki, Tempo/Jaeger) and Open Telemetry.

+ Experience with API gateways and request routing (Envoy or equivalent), including streaming responses.

+ Experience with cost management / Fin Ops tooling (Open Cost, Kubecost, or equivalent) and quota/rate-limit enforcement.

+ Familiarity with model/artifact registries and supply-chain scanning (Harbor, MLflow, Trivy/ SBOM ).

+ Proven track record…