Description
Role Overview:
This role is responsible for designing, building, and operating a secure, scalable MCP Server Catalog within Backstage, enabling discoverability, governance, and self-service access to MCP servers and tools across AWS environments.
You'll bring deep expertise in cloud-native security architecture, API authentication/authorization, and developer platform engineering. You'll drive the implementation of a centralized MCP catalog experience, from registration and metadata management to access control integration, working with identity systems and existing authorization services to enforce policy at scale.
This is a hands-on role. You'll write production code, contribute architectural guidance, and collaborate across application, infrastructure, identity, and operations teams to deliver secure, resilient platform capabilities for the enterprise.
Key Responsibilities
- Design and implement a Backstage-based MCP Server Catalog enabling discoverability, metadata management, lifecycle governance, and developer self-service for Model Context Protocol (MCP) servers and tools.
- Define and implement authentication and authorization patterns for MCP server access across AWS cloud environments, integrating with existing enterprise IAM and authorization services, with consideration for AI agent access models and tool-level permissions.
- Design and develop cloud-native, AI-ready platform components and tooling using clean, efficient, well-documented, and supportable code, supporting scalable LLM and agent integrations.
- Establish enterprise-level architecture for MCP registration, discovery, access control, and usage governance, ensuring alignment with AI platform security and compliance requirements.
- Integrate Backstage with identity providers to support secure, scalable access governance, including support for human users, services, and AI agents.
- Drive continuous improvement and operational maturity for the MCP Catalog platform, including monitoring, reliability, performance, and AI workload observability enhancements.
- Coordinate across infrastructure, application, DevEx, AI platform, and security monitoring teams to ensure secure, compliant, and timely delivery of MCP and AI-enabled solutions.
- Create and maintain comprehensive system documentation for MCP catalog architecture, authorization flows, AI access patterns, installation, configuration, and troubleshooting.
- Define and enforce security standards, governance policies, and access controls for MCP server onboarding, AI tool exposure, and lifecycle management, including risk assessment for model and tool misuse.
- Lead implementation efforts for platform enhancements, upgrades, and AI capability expansion initiatives, including support for evolving MCP specifications and LLM integrations.
- Act as a trusted advisor to leadership on platform security architecture, AI governance trade-offs, and long-term strategy for developer and AI tooling ecosystems.
- Mentor and guide junior engineers, providing technical leadership in cloud-native and AI platform design, and supporting organizational and leadership directives.
- Participate in and conduct code reviews to maintain code quality, adherence to coding standards, and knowledge sharing across cloud, platform, and AI-related components.
- Collaborate with teams in the EST timezone one week each month, ensuring effective coordination, knowledge transfer, and support across geographies.