Lead AI Software Architect — Universal Agent Control

EY; Buffalo (NY); On-site; USD 126,000 - 230,000; Full time

Benefits offered by this job

Hybrid work environment

Competitive compensation

Comprehensive benefits package

Job summary

EY is seeking an experienced Lead AI Software Architect to spearhead a team of domain architect experts in designing and implementing AI Agent Control. The role focuses on building universal agentic control harnesses, post-training environments, and federated learning.

You will guide architecture for identity, auth, and synthesis models, while benchmarking with agent and human evals. You will collaborate with AI, Security, Data and Infrastructure teams, mentor engineers, and contribute to IP

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) and software languages (Go, Rust, Java).

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 these architectures benchmarking performance against agent and human designed evals.
• Lead a team of experts in building a universal agentic control harnesses.

Skills

Analytical thinking

Leadership abilities

Cross-functional collaboration

Emotional intelligence

Problem solving

Education

Advanced degree in Electrical Engineering, Computer Science or Mathematics

Tools

Cursor

Claude Code

Qodo/Codium

Gemini

AWS Q

GitHub

Python

Bash

Typescript

Go

Rust

Java

Job description

EY is seeking an experienced Lead AI Software Architect to spearhead a team of domain architect experts in designing and implementing AI Agent Control. The role focuses on building universal agentic control harnesses, post-training environments, and federated learning.

You will guide architecture for identity, auth, and synthesis models, while benchmarking with agent and human evals. You will collaborate with AI, Security, Data and Infrastructure teams, mentor engineers, and contribute to IP