Intellias

Policy engineer for AI agent platforms

In short

This remote role designs and implements fine-grained authorization policies for AI agent platforms and cloud-native services, centered on Cedar policy language, AWS AgentCore Policy, and identity provider integrations (Entra, Okta, Cognito). It demands 3+ years of security or backend engineering experience, strong Python skills for policy validation tooling, and hands-on work with ABAC/RBAC and OPA or Cedar. The company is a large IT services/outsourcing firm (Intellias) hiring for a senior security-focused engineering position.

Description
We are looking for a Policy Engineer to design, implement, and validate fine-grained authorization policies for AI agent platforms and cloud-native services. The role focuses on Cedar policy development, identity provider integrations, policy enforcement, and attribute-based access control. The ideal candidate combines hands-on security engineering experience with strong Python skills and a deep understanding of modern authorization architectures.
Responsibilities
•Design, implement, and maintain authorization policies using Cedar policy language.
•Develop and test policy definitions, validation workflows, and policy enforcement mechanisms.
•Configure and manage AWS AgentCore Policy in LOG_ONLY and ENFORCE modes.
•Build Python-based tooling for policy validation, testing, and governance.
•Integrate authorization frameworks with Microsoft Entra ID and other identity providers.
•Design claims mapping and token-based authorization flows using OAuth 2.0 and JWT.
•Implement fine-grained and parameter-level access control models.
•Develop and maintain ABAC and RBAC authorization patterns for platform services and AI agents.
•Partner with platform and security teams to ensure secure access governance across distributed systems.
•Create auditability and traceability mechanisms for authorization decisions.
•Support adoption of policy-as-code practices and authorization best practices.
Requirements
•Cedar policy language — authoring and testing
•AWS AgentCore Policy LOG_ONLY / ENFORCE modes
•Python (policy validation tooling)
•MS Entra claims mapping
•Parameter-level access control patterns
•3+ years security engineering or backend engineering
•Identity provider integration (Entra, Okta, Cognito)
•Policy definition in any ABAC or RBAC system
•Open Policy Agent (OPA) or Cedar hands-on
Nice to have
•LangGraph tool invocation patterns
•AWS AgentCore Gateway integration
Conditions
By creating a comfortable atmosphere in our team, we empower individuals to unlock their true potential and achieve extraordinary results. That's why we offer a range of benefits that support your well-being and charge your professional growth. We are committed to fostering equity, diversity, and inclusion as an equal opportunity employer.

Stop applying.
Get referred.

$10 in free credits

In just 60 seconds, fully on autopilot — Eraldt's AI agents read your CV, map the roles you fit, find live vacancies and the people who can refer you, write personal emails, and get you referred.

This isn't an application: your CV doesn't go to the company, and we don't promise a referral for this exact role.

Discover who else lands interviews on autopilot