DevOps Engineer (SC)
Essential:
- Active security clearance.
- AWS cloud engineering (compute, networking, IAM, VPC design, storage).
- Infrastructure-as-Code with Terraform (modular design, environment provisioning, compliance).
- Containerisation using Docker and orchestration with Kubernetes/EKS.
- Deploy and operate ML/LLM inference services on AWS (EKS, ECS, API Gateway, Lambda).
- Implement model-aware CI/CD with artifact packaging, versioning, promotion, and registry integration for approvals, traceability, and rollback.
- Monitor AI workloads, including endpoint performance, resource utilization, logging, and model behavior metrics.
- Support advanced deployment strategies such as blue/green, canary, and shadow deployments.
- Enable Responsible AI operations through audit logging, drift monitoring, and performance alerting.
- Ensure secure AI operations with IAM controls, encrypted artifacts/data flows, and LLM guardrails (eg, Bedrock Guardrails).