Senior AI Infrastructure Engineer – Enterprise Cloud

Grailbio; Edison (CA); Hybrid; USD 169,000 - 224,000; Full time

Job summary

GRAIL in Sunnyvale, CA, is seeking a Staff Software Development Engineer to lead the enterprise AI infrastructure on AWS/EKS. The role requires building a governed AI platform with secure, scalable agentic workflows and multi‑agent orchestration.

You will collaborate with cross‑functional teams including Product, Security, Regulatory, and Data Science to design and implement MCP integrations, IAM governance, and policy controls while mentoring engineering teams.

Qualifications

• 8–12 years of software development and cloud infrastructure experience with demonstrated technical leadership.
• Deep expertise in AWS cloud architecture and container orchestration (EKS) and network isolation.
• Proven experience in agentic AI development and LLM tool-calling workflows.
• Strong IAM, OAuth, JWT with enterprise IdPs (Okta/Auth0) for scoped authorization.
• Hands-on experience with IaC (Terraform/AWS CDK) and CI/CD pipelines.
• Experience with vector databases, RAG architectures, and secure tool integrations.

Responsibilities

• Lead end-to-end design, development, deployment, and monitoring of a scalable enterprise AI platform on AWS EKS.
• Design and implement agentic AI workflows and multi-agent systems with LLM orchestration.
• Architect secure API/tool integrations using MCP to connect AI platform with internal systems and third-party apps.
• Enforce zero-trust access and deterministic policy controls at the API gateway level.
• Develop isolated, scalable container runtimes for secure AI model execution and knowledge retrieval.
• Mentor engineers and collaborate with Product, Security, Regulatory, and Compliance teams.

Skills

AWS

Kubernetes

Python

Go/TypeScript

LLM orchestration

IAM/OAuth/JWT

Terraform

MCP integration

Education

Bachelor's degree in Computer Science or related field

Tools

AWS Bedrock

OpenSearch

KMS

Terraform

AWS CDK

Okta

Auth0

PrivateLink

LangChain

Job description

GRAIL in Sunnyvale, CA, is seeking a Staff Software Development Engineer to lead the enterprise AI infrastructure on AWS/EKS. The role requires building a governed AI platform with secure, scalable agentic workflows and multi‑agent orchestration.

You will collaborate with cross‑functional teams including Product, Security, Regulatory, and Data Science to design and implement MCP integrations, IAM governance, and policy controls while mentoring engineering teams.