Lead DevOps Engineer – AI, GPU

• Build and operate CI/CD/CV pipelines for AI services, agents, and runtime components, including automated build, test, continuous verification, release, and rollback
• Own governance and discovery for AI assets, including service registries, experiment tracking, model metadata, upstream registries, CVE/SBOM scanning, lineage contracts, and license management
• Own resource and cost management, including quotas, rate limits, cost attribution, and utilization
• Own the observability stack covering metrics, logs, traces, dashboards, LLM debugging/evaluation, and SLA/alert notifications
• Own the OpenTelemetry collection layer, including multi-tenant receivers, exporters, queues, GPU telemetry, batching, and dynamic filtering
• Automate GitOps-based delivery and continuous verification with quality, integrity, and cost gates
• Use telemetry, evaluation, and cost signals to drive deployment decisions, progressive rollout, and automated rollback
• Ensure cost and telemetry are identity-stamped and attributable per tenant end-to-end

• Strong DevOps expertise in CI/CD/CV pipeline design, GitOps, 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 in metrics, logs, traces, and OpenTelemetry
• Ability to attribute, bound, and optimize AI consumption cost per tenant and workload
• Familiarity with model/artifact governance, registries, CVE scanning, and license/lineage tracking
• Experience operating across cloud, on-prem, edge, and air-gapped environments
• Bachelor’s or Master’s degree in Computer Science or related technical field
• 8+ years in DevOps, MLOps, platform, or observability engineering, with hands-on production ownership of AI or high-throughput services
• Hands-on experience with ArgoCD, Helm, GitHub Actions/GitLab CI, or equivalents
• Hands-on expertise with Ray Serve, vLLM, Triton, or NIM on GPU infrastructure
• Experience with Prometheus, Grafana, Loki, Tempo/Jaeger, and OpenTelemetry
• Experience with API gateways and request routing such as Envoy, including streaming responses
• Experience with OpenCost, Kubecost, or equivalent, and quota/rate-limit enforcement
• Familiarity with Harbor, MLflow, Trivy/SBOM, and supply-chain scanning
• Experience operating AI or service infrastructure under compliance, security, or regulatory constraints
• Ability to define ownership boundaries and consumption contracts with platform, trust, and data teams