Загрузи резюме, чтобы видеть мэтчи с вакансиейЗагрузи резюме, чтобы видеть мэтч с вакой
подготовься к отклику
ai-инструменты
Чтобы адаптировать резюме под вакансию или составить сопроводительное письмо, загрузи резюме
описание
The Enterprise Agent Development Platform is a production-grade, cloud-native ecosystem that enables engineering teams to define, orchestrate, deploy, and observe AI agents at scale. It unifies agent development across the organization using LangGraph and Strands Agents on AWS AgentCore Runtime, covering agent framework design, runtime architecture, marketplace integration, CI/CD automation, and enterprise-grade observability. The platform reduces agent development time from months to days while enforcing consistent security, quality, and governance standards.
задачи
Define and maintain the agentic versioning model, treating agent container images, prompt configurations, tool bindings, and policy associations as a single immutable unit
Manage AWS AgentCore Runtime versioning, including automatic version creation upon image push and management of DEFAULT and named endpoints
Architect and enforce the agent promotion workflow from dev to qa to prod, embedding evaluation gates to ensure quality before production release
Build agent rollback patterns that restore prior agent versions and confirm that the previous version remains functional
Configure AWS ECR for agent images, addressing ARM64 tagging, lifecycle policies, and image signing to safeguard agent immutability
Integrate with the Agent Registry to automatically register agent versions with metadata such as evaluation outcomes and promotion status
Partner with engineering teams to standardize versioning and lifecycle practices across the agent estate
требования
5+ Years of experience in MLOps or DevOps engineering with AI/ML systems
Hands-on expertise in deployment, promotion, or rollback workflows specifically built for AI agents, such as agent evaluation gates, agent version comparison, or agent endpoint management
Background in versioning and lifecycle management for LLM agents or ML models
Proficiency in immutable artifact versioning at enterprise scale using ECR and model registries
Skills in CI/CD pipeline design with quality gates applied to AI systems
English proficiency at B2 level or higher
Будет плюсом: hands-on competency in AWS AgentCore Runtime versioning, familiarity with agent evaluation frameworks including Langfuse, LangSmith, and PromptLayer, expertise in multi-environment agent promotion patterns, capability to perform agent version comparison and regression detection
