Staff Software Development Engineer - Enterprise AI Infrastructure - #4898

GRAIL is seeking a Staff Software Development Engineer to lead the design, development, and scaling of a governed enterprise AI platform on AWS and Kubernetes. The role involves building agentic AI workflows, multi-agent systems, and secure integrations with enterprise tools. The position requires deep expertise in cloud infrastructure, AI governance, and container orchestration within a regulated healthcare environment.

• Lead end-to-end design, development, deployment, and monitoring of scalable enterprise AI platform using Amazon EKS and AWS services (Bedrock, OpenSearch Serverless, KMS, VPC).
• Design and implement agentic AI workflows, autonomous agents, and multi-agent systems using LLM orchestration techniques.
• Architect secure integrations using Model Context Protocol (MCP) to connect AI platform with internal systems and third-party SaaS.
• Enforce identity, authorization, and zero-trust token brokering flows with Okta, Auth0, and custom JWT authorizers.
• Implement deterministic policy controls for role-based access and human-in-the-loop checks.
• Develop isolated containerized runtime environments for secure AI model execution.
• Establish audit trails and observability using AWS CloudTrail and OpenTelemetry.
• Collaborate with cross-functional stakeholders to translate enterprise requirements into compliant AI solutions.
• Mentor engineers and promote IaC best practices.