Описание
The client is a large global enterprise investing in cloud, data, and AI capabilities. The project builds an enterprise-grade AI Agent Platform for developing, deploying, orchestrating, securing, and observing AI agents across teams and use cases.
Задачи
•Design and implement an agentic versioning model for container images, prompt configurations, tool bindings, and policy associations as immutable versioned artifacts
•Implement AWS AgentCore Runtime version management, including automatic version creation and endpoint management
•Build agent promotion workflows across development, QA, and production with evaluation and quality gates
•Define and implement rollback mechanisms for restoring previous agent versions and validating their functionality
•Manage agent container images in AWS ECR, including ARM64 tagging, lifecycle policies, image signing, and immutability controls
•Integrate versioning workflows with an Agent Registry and automatically register new agent versions and associated metadata
•Capture and maintain evaluation results, promotion status, and version information
•Design CI/CD pipelines that enforce quality and evaluation gates for AI systems
•Support version comparison and regression detection across agent releases
Требования
•5+ Years of MLOps or DevOps engineering experience with AI/ML systems
•Experience with versioning and lifecycle management for LLM agents or ML models
•Experience with immutable artifact versioning at enterprise scale, including ECR and model registries
•Experience designing CI/CD pipelines with quality gates for AI systems
Nice to have: AWS AgentCore Runtime versioning hands-on experience, agent evaluation frameworks such as Langfuse, LangSmith, and PromptLayer, multi-environment agent promotion patterns, agent version comparison and regression detection.
Условия
Remote work is available from Bulgaria, Croatia, Egypt, India, Poland, Portugal, Spain, or Ukraine. Intellias offers benefits supporting well-being and professional growth.
