Lead AI Architect: Multi-Agent Control

EY; McLean (VA); Hybrid; USD 144,000 - 329,000; Full time

Benefits offered by this job

Medical & Dental

401(k) plan

Paid time off

Hybrid work model

Flexible vacation

Job summary

EY seeks an experienced Lead AI Software Architect to lead a team of domain architects in designing AI Agent Control. You will oversee tool usage, state management, environment control, policy definition, multiagent API, and anomaly detection to support scalable AI solutions.

You will drive designs for identity/authentication, telemetry, and secure logging, while collaborating across AI, Security, Data, and Infra.

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 (Cursor, Claude Code, Qodo/Codium, Gemini, AWS Q, GitHub)
• Familiarity with scripting languages (Python, Bash, Typescript etc…) and software languages (Go, Rust, Java etc…).
• Understand AI Native design process and principles
• Experience with cryptographic methods of identity and auth.
• Experience with modern software IDE, CI/CD pipeline, modern code hosting and collaboration (Github/Gitlab/Azure DevOps etc…)
• Experience with Nvidia NVAIE, AWS and MSFT Azure AI stacks.

Responsibilities

• Design control harness intelligence systems for multiagent frameworks.
• Create architectures for agent identity and authentication at scale.
• Develop post-training and tuning environments.
• Design synthesis models for AI open-source models.
• Implement and test architectures benchmarking performance against evals.
• Build comprehensive AI Agent control frameworks.
• Lead AI Native design processes and agent design requirements.
• Research emerging agent authorization architectures and frontier models.
• Collaborate with AI, Security, Data and Infra teams for balanced outcomes.
• Support strategic business development for emerging tech as needed.
• Present at academic conferences and support IP filings.
• Hands-on development of advanced AI capabilities in agentic control.
• Lead a team of experts building universal agentic control harnesses.

Skills

Multi-agent systems

AI software development

Python

Go

Java

Leadership

Mentoring

Education

Advanced degree in Electrical Engineering, Computer Science or Mathematics

Tools

Cursor

Claude Code

Qodo/Codium

Gemini

AWS Q

GitHub

GitLab

Azure DevOps

Nvidia NVAIE

Job description

EY seeks an experienced Lead AI Software Architect to lead a team of domain architects in designing AI Agent Control. You will oversee tool usage, state management, environment control, policy definition, multiagent API, and anomaly detection to support scalable AI solutions.

You will drive designs for identity/authentication, telemetry, and secure logging, while collaborating across AI, Security, Data, and Infra.