Platform Engineer – Agent Promotion & Rollback

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. They are actively investing in modern cloud, data, and AI capabilities. The project involves building an enterprise-grade AI Agent Platform from the ground up to provide standardized AI agent development, deployment, orchestration, security, and observability across multiple teams and use cases.

• Experience with agent promotion workflow across environment progression (dev → QA → prod) with evaluation gate enforcement.
• Experience with agent rollback mechanisms including validation (health check, smoke test).
• Experience managing AWS AgentCore Runtime endpoints (DEFAULT alias, environment pinning).
• Experience enforcing agent evaluation gates blocking promotion if agents fail quality checks (PII safety, workflow accuracy).
• Experience with agent version comparison running evaluation suites to detect regression.
• Strong Python automation skills for agent lifecycle operations.
• 4+ years platform or backend engineering experience with AI/ML systems.
• Experience with multi-environment deployment and promotion workflows.
• Experience in rollback automation and safety validation.
• Experience enforcing quality gates in deployment pipelines.

Nice to have:

• Hands-on usage of AWS AgentCore Evaluation API.
• Experience with agent regression testing and version comparison.
• Experience with blue/green or canary deployment patterns for LLM agents.
• Experience with agent health monitoring post-deployment.

• Design and implement agent promotion workflows across development, QA, and production environments.
• Build automated quality gates to validate agents before promotion.
• Implement rollback mechanisms to restore previous production agent versions.
• Automate post-deployment validation including health checks and smoke tests.
• Manage AWS AgentCore Runtime versions and endpoints.
• Build Python automation for agent deployment, promotion, versioning, and rollback.
• Integrate agent evaluation results into deployment pipelines to prevent releases failing 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.
• Monitor agent health 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.

Przesyłając ten formularz, wyrażasz zgodę na przetwarzanie Twoich danych osobowych zgodnie z naszą Polityką Prywatności Rekrutacji - https://career.intellias.com/recruitment-privacy-notice. Jeśli chcesz wycofać swoją zgodę lub masz jakiekolwiek pytania dotyczące naszej Polityki Prywatności Rekrutacji, skontaktuj się z nami([email protected])