Platform Engineer – Agent Promotion & Rollback

We are looking for a Platform Engineer to build and automate agent deployment, promotion, and rollback capabilities for an enterprise AI Agent Platform being developed from the ground up.

The role will focus on creating reliable multi-environment release workflows for AI agents, introducing automated quality gates, version management, regression validation, and safe rollback mechanisms to ensure agents can progress from development to production in a controlled and predictable way.

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 agent promotion workflows across development, QA, and production environments.
• Build automated quality gates that validate agents before promotion to higher environments.
• Implement rollback mechanisms to safely restore previous production agent versions.
• Automate post-deployment validation including health checks and smoke tests.
• Manage AWS AgentCore Runtime versions and endpoints to support environment-specific deployments.
• Build Python automation for agent deployment, promotion, versioning, and rollback operations.
• Integrate agent evaluation results into deployment pipelines to prevent releases that fail quality, safety, or workflow accuracy checks.
• Implement agent version comparison and regression testing using consistent evaluation suites.
• Support safe deployment strategies such as blue/green and canary patterns for AI agents.
• Monitor agent health following deployments and support automated detection of release issues.
• Collaborate with AI and platform engineering teams to establish reliable CI/CD and lifecycle management practices for agents.

• Agent promotion workflow — environment progression (dev → qa → prod) with evaluation gate enforcement

• Agent rollback mechanism — revert production agent to previous version with validation (health check, smoke test)

• AWS AgentCore Runtime endpoint management — DEFAULT alias for latest, named endpoints for environment pinning

• Agent evaluation gates — block promotion to qa/prod if agent fails quality checks (PII safety, workflow accuracy)

• Agent version comparison — run same evaluation suite against two agent versions to detect regression

• Python automation for agent lifecycle operations

• 4+ years platform or backend engineering with AI/ML systems

• Multi-environment deployment and promotion workflows

• Rollback automation and safety validation

• Quality gate enforcement in deployment pipelines

• AWS AgentCore Evaluation API hands-on usage

• Agent regression testing and version comparison

• Blue/green or canary deployment patterns for LLM agents

• Agent health monitoring post-deployment