Senior AI Engineer - Agentic

The University of Louisville is seeking a Senior AI Engineer to lead the design and delivery of secure, end-to-end multi-agent AI systems for high-stakes, security-sensitive environments. The role focuses on multi-agent orchestration, distributed inference, delegated authorization, standardized agent protocols, adaptive user interfaces, and compliance, while also providing technical leadership, mentorship, and research contributions.

Responsibilities:

• Architect and build end-to-end agentic AI systems, spanning model training, distributed inference, authentication/authorization, and the user-facing applications people actually touch, for production-grade, ultra-secure environments
• Design multi-agent orchestration: a central orchestrator coordinating distributed specialist agents (e.g., retrieval, records, vision) over a bidirectional, low-latency, stateful transport (e.g., WebSockets)
• Implement a delegated-authority / scoped-authorization model (e.g., OAuth 2.0 Token Exchange) so every agent action carries an explicit, narrowly scoped, auditable actor claim, closing the accountability gap created when agents impersonate users
• Develop standardized agent communication and tool-use protocols (e.g., Model Context Protocol and Agent-to-Agent / A2A), extending them with structured UI primitives
• Build a platform-agnostic, server-driven interface and response-translation layer that adapts structured outputs to the connecting device (desktop, smartwatch, voice/ambient, robotics)
• Ensure security, compliance, and auditability for AI operating in regulated, high-stakes domains
• Provide technical leadership, mentor junior engineers and students, and contribute to peer-reviewed research and open-source releases
• Work within secure environments that handle sensitive data: apply cybersecurity best practices and institutional security and compliance controls (e.g., HIPAA, NIST 800-53) across every system built and operated