Senior Platform Engineer - Generative AI w Warząchewka Polska, Polska

We are looking for a Senior Platform Engineer - Generative AI to join our team building an Enterprise Agent Development Platform — a production-grade, cloud-native ecosystem that enables engineering teams to define, orchestrate, deploy, and observe AI agents at scale. The platform standardizes agent development across the organization using LangGraph and Strands Agents on AWS AgentCore Runtime. The initiative spans agent framework design, runtime architecture, marketplace integration, CI/CD automation, and enterprise-grade observability — reducing agent development from months to days while enforcing consistent security, quality, and governance standards.

Implement agent promotion workflows across environment progression (dev to qa to prod) with evaluation gate enforcement Build agent rollback mechanisms to revert production agents to previous versions with validation such as health checks and smoke tests Manage AWS AgentCore Runtime endpoints, including DEFAULT alias for latest versions and named endpoints for environment pinning Enforce agent evaluation gates to block promotion to qa/prod when agents fail quality checks such as PII safety and workflow accuracy Run agent version comparisons by executing the same evaluation suite against two agent versions to detect regression Develop Python automation for agent lifecycle operations 3+ years of platform or backend engineering experience with AI/ML systems Hands-on experience with agent promotion, evaluation-gate, or rollback workflows in a production agentic AI project, such as AWS AgentCore Runtime endpoint/alias management, agent version comparison for regression detection, or blue/green rollback for LLM agents Experience with multi-environment deployment and promotion workflows Experience with rollback automation and safety validation Experience with quality gate enforcement in deployment pipelines English proficiency at B2 level or higher Familiarity with AWS AgentCore Evaluation API hands-on usage Experience with agent regression testing and version comparison Knowledge of blue/green or canary deployment patterns for LLM agents Experience with agent health monitoring post-deployment