Senior AI Agent Control Architect

Ernst & Young Oman; Jacksonville (FL); Hybrid; USD 126,000 - 262,000; Full time

Benefits offered by this job

Hybrid work model

Medical and dental coverage

Pension and 401(k) plans

Paid time off

Job summary

EY seeks an experienced agent AI Software Architect to design and implement AI Agent Control. The role covers authentication, tool usage, state management, execution control, and policy definition for multi-agent systems.

You will lead architecture for identity, post-training environments, and synthesis models, working with AI, security, data and infra teams to deliver scalable AI solutions.

Qualifications

• Advanced degree in a relevant field and 5+ years in software engineering and AI.
• Experience with multi-agent systems and modern secrets management.
• Familiar with AI native development tools and cryptographic identity methods.

Responsibilities

• Design architectures for agent identity and authentication in large scale multi-agent systems.
• Design post training and tuning/customization environments.
• Design synthesis models for AI open source models.
• Implement and test architectures benchmarking performance against evals.
• Develop comprehensive AI Agent control frameworks.
• Drive agent design requirements through AI Native processes.
• Research emerging authorization architectures and frontier models.
• Collaborate with AI, Security, Data and Infrastructure teams for practical outcomes.
• Support strategic business development and IP filings.
• Hands-on development of advanced AI capabilities in agentic control.

Skills

Analytical skills

Leadership

Cross-functional collaboration

Critical thinking

Emotional intelligence

Hybrid collaboration

Education

Advanced degree in Electrical Engineering, Computer Science or Mathematics

Tools

NVIDIA NVAIE

AWS AI stack

Azure AI stack

AI native development tools (Cursor, Claude Code, Qodo/Codium, Gemini, AWS Q, GitHub)

Job description

EY seeks an experienced agent AI Software Architect to design and implement AI Agent Control. The role covers authentication, tool usage, state management, execution control, and policy definition for multi-agent systems.

You will lead architecture for identity, post-training environments, and synthesis models, working with AI, security, data and infra teams to deliver scalable AI solutions.