Lead AI Architect - Universal Agent Control Harness

EY; Indianapolis (IN); Hybrid; USD 126,000 - 230,000; Full time

Benefits offered by this job

Hybrid work model

Flexible vacation policy

Paid holidays

Job summary

EY is seeking an experienced Lead AI Software Architect to guide a team of domain architects in designing and implementing AI Agent Control. The role emphasizes scalable agentic systems, tool usage, state management, authentication, observability, and anomaly detection.

You will shape architectures for multi-agent identity, post-training environments, and AI stacks, collaborating with AI, Security, Data, and Infra experts. EY offers a hybrid work model and a diverse, inclusive culture.

Qualifications

• Advanced degree in Electrical Engineering, Computer Science or Mathematics.
• 10+ years of experience in software engineering and AI.
• Experience with multi-agent system administration and modern secrets management.
• Use of AI native software development tools / code assist.
• Familiarity with scripting languages (Python, Bash, Typescript) and software languages (Go, Rust, Java).
• Understand AI Native design process and principles.
• Experience with cryptographic methods of identity and auth.
• Experience with modern software IDE, CI/CD pipeline and collaboration tools.
• Experience with Nvidia NVAIE, AWS and MSFT Azure AI stacks.

Responsibilities

• Design control harness intelligence systems including multiagent systems and tools.
• Design architectures for agent identity and authentication in large scale multi-agent enterprise systems.
• Design post training and tuning/customization environments.
• Design synthesis models for AI open-source models.
• Implement and test architectures benchmarking performance against evals.
• Design comprehensive AI Agent control frameworks.
• Drive agent design requirements through AI Native design process.
• Assess emerging agent authorization architectures and frontier model proposals.
• Collaborate with AI, Security, Data and Infra teams for balanced outcomes.
• Support strategic business development for emerging technology.
• Present at academic conferences and support IP filings.
• Hands-on development of advanced AI capabilities in agentic control.
• Lead a team of experts in building universal agentic control harnesses.

Skills

Leadership

Architectural design

AI agent control

Multi-agent systems

Security & auth

CI/CD

Cloud stacks

Education

Advanced degree in Electrical Engineering, Computer Science or Mathematics

Tools

Cursor

Claude Code

Qodo/Codium

Gemini

AWS Q

GitHub

Job description

EY is seeking an experienced Lead AI Software Architect to guide a team of domain architects in designing and implementing AI Agent Control. The role emphasizes scalable agentic systems, tool usage, state management, authentication, observability, and anomaly detection.

You will shape architectures for multi-agent identity, post-training environments, and AI stacks, collaborating with AI, Security, Data, and Infra experts. EY offers a hybrid work model and a diverse, inclusive culture.