Lead DevOps Engineer (AI & GPU)
New
Z
ZimperiumAI infrastructure
Listing location: Bangalore, India; Workplace type: RemoteFull-TimeLead
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 8+ years in DevOps, MLOps, platform, or observability engineering
- Required Skills
- GrafanaPrometheusCI/CD
Requirements
- Hold a Bachelor’s or Master’s degree in Computer Science or a related technical field.
- Have 8+ years in DevOps, MLOps, platform, or observability engineering, with hands-on production ownership of AI or high-throughput services.
- Bring strong DevOps experience with CI/CD/CV pipelines, GitOps, continuous verification, and automated release and rollback.
- Have hands-on experience with GitOps tooling such as ArgoCD, Helm, GitHub Actions, or GitLab CI, or equivalents.
- Operate inference and model-serving frameworks such as Ray Serve, vLLM, Triton, or NIM on GPU infrastructure.
- Have experience with observability stacks such as Prometheus, Grafana, Loki, Tempo or Jaeger, and OpenTelemetry.
- Have experience with API gateways and request routing, such as Envoy or equivalent, including streaming responses.
- Have experience with cost management or FinOps tooling and quota or rate-limit enforcement.
- Be familiar with model and artifact registries and supply-chain scanning, including Harbor, MLflow, and Trivy/SBOM.
- Have a track record operating AI or service infrastructure under compliance, security, or regulatory constraints.
- Be able to define ownership boundaries and consumption contracts with platform, trust, and data teams.
Responsibilities
- Build and operate CI/CD/CV pipelines for AI services, agents, and runtime components, including automated build, test, verification, release, and rollback.
- Manage governance and discovery for AI assets, including service catalogs, registries, model metadata, scanning, lineage, and license management.
- Manage quotas, rate limits, cost attribution, and utilization for AI execution per tenant and engagement.
- Operate observability for metrics, logs, traces, dashboards, LLM debugging and evaluation, and SLA alerts.
- Operate the OpenTelemetry collection layer, including receivers, exporters, queues, GPU telemetry, batching, and dynamic filtering.
- Automate GitOps-based delivery and continuous verification, embedding quality, integrity, and cost gates in pipelines.
- Use telemetry, evaluation, and cost signals to guide deployment decisions, progressive rollout, and automated rollback.
- Ensure cost and telemetry are identity-stamped and attributable per tenant.
View Full Description & ApplyYou'll be redirected to the employer's site
