Staff AI Infrastructure Engineer, Enterprise Platform

BioSpace; Durham (NC); Hybrid; USD 147,000 - 195,000; Full time

Job summary

GRAIL seeks a Staff Software Development Engineer - Enterprise AI Infrastructure in a hybrid/onsite role in Durham NC or Menlo Park. Lead the design, deployment, and governance of a centralized AI platform on AWS/EKS with agentic workflows and strict security controls.

You will mentor teams, work across regulatory and security functions, and shape the AI infra roadmap while aligning with enterprise needs and on-site requirements.

Qualifications

• Bachelor’s degree in Computer Science, Software Engineering, AI, or related field; advanced degree preferred.
• 8–12 years of software development and cloud infra experience with leadership.
• Deep AWS architecture, EKS, Kubernetes networking, IAM, KMS, and GenAI services.
• Experience building agentic AI, autonomous agents, and LLM tool calls.
• Hands-on MCP implementation or governance for LLM tool integrations.
• IAM/OAuth/JWT with enterprise IdPs (Okta/Auth0) for scoped access.
• Proficient in Python, TypeScript, or Go; IaC tools like Terraform, AWS CDK.
• Vector databases, RAG architectures, and row-level access controls.
• CI/CD, MLOps, Helm, containerization, observability stacks.

Responsibilities

• Lead design, development, deployment, and monitoring of a scalable AI platform on AWS EKS.
• Design agentic AI workflows and multi-agent orchestration techniques.
• Architect secure integrations using MCP to connect AI platform with internal systems.
• Enforce identity, zero-trust, and policy controls at API gateways.
• Build isolated, scalable container runtimes for secure model execution.
• Maintain audit trails and observability with CloudTrail and OpenTelemetry.
• Collaborate with Product, Security, Regulatory, and Stakeholders on infra solutions.
• Mentor engineers and promote IaC and engineering excellence.
• Coordinate with Compliance and Privacy to meet regulatory requirements.

Skills

AWS

Kubernetes

LangChain

LangGraph

AutoGen

Claude Agent SDK

MCP

IAM

OAuth

JWT

Python

TypeScript

Go

Terraform

AWS CDK

OpenSearch

FAISS

pgvector

CI/CD

MLOps

Helm

Kubernetes Networking

Education

Bachelor’s degree

Master’s or PhD preferred

Tools

AWS Bedrock

OpenSearch Serverless

KMS

VPC

Job description

GRAIL seeks a Staff Software Development Engineer - Enterprise AI Infrastructure in a hybrid/onsite role in Durham NC or Menlo Park. Lead the design, deployment, and governance of a centralized AI platform on AWS/EKS with agentic workflows and strict security controls.

You will mentor teams, work across regulatory and security functions, and shape the AI infra roadmap while aligning with enterprise needs and on-site requirements.