Senior AI Agent Control Architect & Manager

Ernst & Young Oman; Boston (MA); On-site; USD 126,000 - 230,000; Full time

Benefits offered by this job

Hybrid work model

Medical insurance

401(k) plan

Paid time off

Job summary

EY is seeking an experienced agent AI Software Architect to design and implement advanced AI Agent Control, including authentication, tool usage, and environment control for scalable enterprise systems.

The role emphasizes post-training tuning, synthesis models, and cross-functional collaboration with security, data, and infrastructure teams, while driving innovation in AI-native design across federated learning and IP development.

Qualifications

• Advanced degree in Electrical Engineering, Computer Science or Mathematics.
• 5+ 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 CI/CD pipelines and modern code hosting (Github/Gitlab/Azure DevOps).
• Experience with Nvidia NVAIE, AWS and MSFT Azure AI stacks.

Responsibilities

• Design architectures for agent identity and authentication in large-scale multi-agent systems.
• Design post-training and tuning environments.
• Design synthesis models for AI open source models.
• Implement and test architectures benchmarking agent and human evals.
• Design 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 Infra teams for balanced outcomes.
• Support business development for emerging tech; present at conferences.

Skills

AI architectures

Security & auth

Software design

Cross-functional leadership

Mentoring

Observability

Python scripting

Multi-agent design

Education

Advanced degree in EE/CS/Math

Tools

Cursor

Claude Code

Qodo/Codium

Gemini

AWS Q

GitHub

GitLab

Azure DevOps

Job description

EY is seeking an experienced agent AI Software Architect to design and implement advanced AI Agent Control, including authentication, tool usage, and environment control for scalable enterprise systems.

The role emphasizes post-training tuning, synthesis models, and cross-functional collaboration with security, data, and infrastructure teams, while driving innovation in AI-native design across federated learning and IP development.