Lead DevOps Engineer (AI & GPU)
Core
Own the delivery, model-serving, routing, and observability layer of AI-native platforms across cloud, on-prem, edge, and air-gapped environments.
Role type
Senior IC DevOps/MLOps Engineer (AI & GPU)
Builds
CI/CD/CV pipelines, model-serving runtimes, observability stacks, and governance systems for AI workloads.
Domain
AI/ML Infrastructure, GPU Computing, Cloud-Native Systems
Deliverable
production ML models
Required skills
CI/CD/CV pipeline design, GitOps, GPU model serving (Ray, vLLM, Triton), observability (OpenTelemetry, Prometheus, Loki, Jaeger), FinOps/cost management, API gateway/routing, artifact governance
Preferred skills
LLM evaluation/debugging, sandboxed execution, GPU telemetry optimization, regulated environment delivery
Technologies
ArgoCD, Helm, GitHub Actions, Ray Serve, vLLM, Triton, NIM, Prometheus, Grafana, Loki, Tempo, Jaeger, LangSmith, Langfuse, Envoy, OpenCost, Kubecost, Harbor, MLflow, Trivy, OpenLineage, DCGM, Kafka
Responsibilities
Build and operate CI/CD/CV pipelines for automated build, test, release, and rollback of AI services. Manage governance, discovery, and license tracking for AI assets. Implement resource quotas, rate limits, and cost attribution for AI workloads. Operate full observability stacks including metrics, logs, traces, and LLM debugging tools. Automate GitOps-based delivery with embedded quality and cost gates. Close the loop between telemetry and deployment decisions for progressive rollouts and rollbacks.
Seniority
Senior, hands-on IC