This is a fully remote position, open to applicants in North Carolina.

📋 Description

• Develop and manage the MCP fleet, which includes the shipping, securing, and patching of both self-hosted and managed MCP servers for business applications and databases, as well as overseeing the MCP registry.

• Take ownership of the agent platform's deployment strategies, guardrails, observability, and underlying hosting infrastructure.

• Co-manage the Bedrock runtime and gateway, which encompasses model access, cost attribution, content-filtering guardrails, model pinning, and quota management via an AWS/Okta-SSO'd gateway.

• Create the Bedrock-to-Snowflake pipeline featuring identity matching, usage tracking, and threshold alerting.

• Oversee MDM configuration, desktop client setup, credentials, and authentication processes for non-technical staff.

• Develop AI automations across Claude desktop, Slack, and Google Workspace.

• Direct workflows based on data sensitivity, enforce least privilege access and auditability, and isolate unproven models from production data.

⛳️ Requirements

• A minimum of 6 years in software engineering, platform engineering, or DevOps, including responsibility for a production system relied upon by others.

• Proficient in AWS — including IAM, ECS or Lambda, CloudWatch, and a solid understanding of VPC. This is essential, not optional.

• Full-stack expertise — encompassing backend services, APIs, CI/CD, and containerized deployments.

• Capability to develop an MCP server or API integration from the ground up, rather than merely connecting a managed service.

• Practical experience with LLMs, including LLM APIs, prompt engineering, and agent development; have successfully delivered projects utilizing them.

• Skill in taking loosely defined tasks and identifying the necessary undocumented requirements.