Lead AI Architect — Multi-Agent Systems & Control Harness

Ernst & Young Oman; Irvine (CA); On-site; USD 144,000 - 329,000; Full time

Job summary

EY seeks an experienced Lead AI Software Architect to lead domain experts in designing and implementing AI Agent Control. You will drive architectures for agent identity, authentication, and post-training environments, including governance, telemetry and anomaly detection, with a focus on scalable, secure AI-native solutions.

You will guide a team across AI, Security, Data and Infra, shaping strategy, mentoring engineers, and contributing to IP filings.

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

Responsibilities

• Design control harness intelligence systems for multiagent environments.
• Architect agent identity and authentication for large-scale systems.
• Design post-training and tuning environments for agents.
• Create synthesis models for AI open-source models.
• Implement and benchmark architectures against agent/human evals.
• Develop comprehensive AI Agent control frameworks.
• Drive agent design requirements via AI Native design process.
• Research emerging authorization architectures and frontier models.
• Collaborate with AI, Security, Data, and Infrastructure teams.
• Support strategic business development for emerging tech.
• Present at academic conferences and contribute to IP filings.
• Hands-on development of advanced AI capabilities in agentic control.
• Lead experts in building universal agentic control harnesses.

Skills

AI architecture

Multi-agent systems

Leadership

Authentication design

Observability

Telemetry

Security

Education

Advanced degree in EE/CS/Math

10+ years software engineering & AI

Tools

GitHub

GitLab

Azure DevOps

CI/CD pipelines

AWS

Azure

NVIDIA NVAIE

Job description

EY seeks an experienced Lead AI Software Architect to lead domain experts in designing and implementing AI Agent Control. You will drive architectures for agent identity, authentication, and post-training environments, including governance, telemetry and anomaly detection, with a focus on scalable, secure AI-native solutions.

You will guide a team across AI, Security, Data and Infra, shaping strategy, mentoring engineers, and contributing to IP filings.