Lead AI Architect - Agentic Control Systems

Ernst & Young; Atlanta (GA); Hybrid; USD 144,000 - 329,000; Full time

Benefits offered by this job

Hybrid work model

Medical & dental coverage

401(k) plan

Paid time off

Job summary

Ernst & Young is seeking an experienced Lead AI Software Architect to guide a team of domain experts in building universal agentic control harnesses. The role focuses on agent control, authentication, post-training environments, and scalable architectures for enterprise systems.

You will lead design efforts across AI, security and data teams, mentor engineers, and contribute to IP development. EY offers a hybrid work model with comprehensive compensation and benefits across the US.

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.
• Experience with AI native software development tools/code assist.
• Familiarity with scripting languages (Python, Bash, Typescript) and software languages (Go, Rust, Java).
• Knowledge of AI Native design processes and authentication/identity methods.
• Experience with CI/CD pipelines and modern code hosting (GitHub/GitLab/Azure DevOps).
• Experience with Nvidia NVAIE, AWS and MSFT Azure AI stacks.

Responsibilities

• Design of control harness intelligence systems including multiagent systems and associated tools and scaffolding.
• Design architectures for agent identity and authentication in large scale multi-agent enterprise systems.
• Design of post training and tuning/customization environments.
• Design of synthesis models for AI open-source models.
• Implement and test architectures benchmarking performance against agent and human evals.
• Design comprehensive AI Agent control frameworks.
• Drive agent design requirements and implement through AI Native design process.
• Collaborate with other architectural experts in AI, Security, Data and Infrastructure.

Skills

AI architecture

Multi-agent systems

Identity authentication

Secrets management

AI-native tooling

CI/CD pipelines

Go, Rust, Java

Education

Advanced degree in Electrical Engineering, Computer Science or Mathematics

Tools

Cursor

Claude Code

Qodo/Codium

Gemini

AWS Q

GitHub

GitLab

Azure DevOps

Job description

Ernst & Young is seeking an experienced Lead AI Software Architect to guide a team of domain experts in building universal agentic control harnesses. The role focuses on agent control, authentication, post-training environments, and scalable architectures for enterprise systems.

You will lead design efforts across AI, security and data teams, mentor engineers, and contribute to IP development. EY offers a hybrid work model with comprehensive compensation and benefits across the US.