Staff AI Platform Engineer

The role

Build and run the platform that governs AI models, agents and MCP servers, including model access, cost controls, guardrails and telemetry. Set the technical direction and standards other teams adopt for agent hosting. Work with IT, Security and DevX to get teams building against a written standard.

What you will do

• Drive Bedrock runtime and gateway configuration: model access, cost attribution, content-filtering guardrails, model pinning and quota management
• Build, ship, secure and patch self-hosted and managed MCP servers, and own the MCP registry
• Author the MDM config payload and Okta-group-to-IAM mapping that IT enforces, and specify desktop client setup for non-technical employees
• Build AI and agent-triggered automations such as approvals, spend alerts and agent-initiated workflows
• Own the technical direction and design docs for the agent-hosting substrate
• Define health and safe-to-ship criteria for agents and MCP servers, including cost, usage and reliability telemetry with threshold alerting
• Create a tiered-autonomy model deciding what stays read-only, what can act, and what needs a human or a rollback path
• Build governance that routes workflows by data sensitivity, enforces least privilege and auditability, and sandboxes unproven models
• Align IT, Security and DevX on platform direction through a written standard

Required qualifications

• 6+ years in software engineering, platform engineering or DevOps, including owning something in production that others depended on
• Hands-on AWS: IAM, ECS or Lambda, CloudWatch and working VPC knowledge
• Full-stack range: backend services, APIs, CI/CD and containerized deployments
• Able to write an MCP server or API integration from scratch
• Hands-on with LLMs: LLM APIs, prompt engineering and agent development, with something shipped
• Self-direction to take an underspecified task and resolve its ambiguous parts

Benefits

• Extra days off
• 401(k) Retirement Savings Plan with a 3% company match
• Maternity and Parental Leave
• Mental health support through the Modern Health app
• Full health benefits package for you and your family

Before you apply

• Actual offers may be higher or lower than the stated range, based on work location, experience and education

About the company

Sysdig builds cloud security products, including Falco, the open standard for cloud threat detection. Its technology is trusted by over 60% of the Fortune 500.