DevOps Engineer – Agent CI/CD & Registry

We are looking for a DevOps Engineer to build and automate CI/CD and registry workflows for enterprise AI agents. The role focuses on containerized agent delivery, automated version registration, security and evaluation gates, artifact traceability, and reliable promotion of agent versions across environments.

Our client is a large global enterprise operating across multiple markets, with a complex technology landscape and a strong focus on digital transformation and innovation. The organization is actively investing in modern cloud, data, and AI capabilities to enable scalable, secure, and highly automated solutions across its business.

The project is focused on building an enterprise-grade AI Agent Platform from the ground up. The platform will provide a standardized foundation for developing, deploying, orchestrating, securing, and observing AI agents across multiple teams and use cases.

The initiative covers the full agent lifecycle and brings together agent orchestration, observability, security, governance, integrations, evaluation, and platform engineering. Engineers joining the project will have an opportunity to influence key architectural and technical decisions and contribute to a new platform rather than maintaining an existing solution.

• Design and implement CI/CD pipelines for AI agents, including ARM64 container builds, security scanning, ECR publishing, and AgentCore Runtime version creation.
• Build GitHub Actions workflows supporting matrix builds and automated agent-specific validation.
• Integrate CI/CD pipelines with the Agent Registry, automatically registering agent versions and associated metadata.
• Implement and maintain version metadata, including Git SHA, container digest, timestamps, evaluation results, promotion status, and tool/policy bindings.
• Manage agent container images in AWS ECR, including semantic version tags and Git SHA-based traceability.
• Integrate security scanning into CI/CD pipelines, covering vulnerabilities, secrets, compliance, and agent-specific risks.
• Implement evaluation gates to prevent promotion of agent versions that fail required quality checks.
• Support reliable multi-environment promotion and deployment workflows for agent versions.
• Maintain traceability between source code, container artifacts, evaluation results, registry entries, and deployed agent versions.

• Agent CI/CD pipeline — build ARM64 agent containers, security scan, push to ECR, trigger AgentCore Runtime version creation

• Agent Registry integration — auto-register agent versions with metadata (git SHA, evaluation pass/fail, promotion status)

• GitHub Actions for agent workflows — matrix builds, agent-specific security scans (prompt injection, PII leakage)

• AWS ECR for agent images — semantic versioning tags, git SHA tags for traceability

• Agent version metadata schema — version ID, container digest, timestamp, evaluation results, tool/policy bindings

• 4+ years DevOps or platform engineering with AI/ML pipelines

• CI/CD pipeline implementation for containerized AI agents or ML models

• Container registry management and tagging strategies

• Security scanning in CI/CD (vulnerabilities, secrets, compliance)

• AWS AgentCore Runtime endpoint management API

• Agent evaluation gate integration (block promotion if evaluation fails)

• GitOps promotion patterns for agents

• LangChain/LangGraph agent packaging and deployment