Lead AI Agent Engineer—Autonomy & Safety

EY; Chantilly (VA); Hybrid; USD 126,000 - 230,000; Full time

Benefits offered by this job

Hybrid work arrangement

Travel up to 50%

Competitive compensation package

Job summary

EY is seeking a senior individual to build AI agents that operate across complex workflows with safety and observability. You will shape execution models, tool interfaces, and durable contexts while ensuring controlled access in production environments.

The role sits at the intersection of applied AI, distributed systems, and product engineering, requiring hands-on delivery of long-running agent workflows and enterprise integrations with a focus on reliability and measurable outcomes.

Qualifications

• 7-9 years of experience in software or applied machine-learning engineering, with ownership of production systems and their live behavior.
• Hands-on evidence of shipping large-language-model applications, agents, or complex model-driven workflows used for real work.
• Strong capability in Python, TypeScript, or production services languages.
• Applied AI patterns including model APIs, structured outputs, retrieval, tool use, and evaluation of variable behavior.

Responsibilities

• Choose the right execution model and design agent architectures for deterministic steps when justified by performance.
• Build dependable tools with clear contracts, validated outcomes, and bounded authorization.
• Engineer agent behavior across planning, routing, delegation, stopping, retry, and handoff in full workflows.
• Create durable context using instructions, user state, retrieval, memory, and environment feedback.
• Bound agent authority with scoped identities, credentials, budgets, and emergency containment.
• Evaluate complete trajectories with tests for verified task success, recovery, and restricted actions.
• Operate long-running execution with durable state, checkpointing, and safe retries.
• Make behavior observable with end-to-end traces and production insights.
• Protect user control with clear intervention points for inspection and safe resumption.
• Publish reusable agent patterns and lessons with cross-team collaboration.

Skills

Seven to nine years experience

Python

TypeScript

Model APIs

Distributed systems

Production systems ownership

Security and access

Education

Bachelor’s Degree in a relevant field

Job description

EY is seeking a senior individual to build AI agents that operate across complex workflows with safety and observability. You will shape execution models, tool interfaces, and durable contexts while ensuring controlled access in production environments.

The role sits at the intersection of applied AI, distributed systems, and product engineering, requiring hands-on delivery of long-running agent workflows and enterprise integrations with a focus on reliability and measurable outcomes.